Elite Las Vegas SEO Group 2

The Magical Black Box

Aaron Wall — Sun, 24 Sep 2023 00:43:05 -0700

Google's mission statement is "organize the world's information and make it universally accessible and useful."

That mission is so profound & so important the associated court documents in their antitrust cases must be withheld from public consumption.

Hey. The full exhibit list just posted in DC federal court for USA vs Google. J/k, they literally posted the numbers of all of the admitted exhibits which would be unsealed in a sane world where public interest is respected even more so because the defendant is insanely powerful. pic.twitter.com/FViD40xVmf— Jason Kint (@jason_kint) September 23, 2023

Before document sharing was disallowed, some were shared publicly.

Internal emails stated:

Hal Varian was off in his public interviews where he suggested it was the algorithms rather than the amount of data which is prime driver of relevancy.
Apple would not get any revshare if there was a user choice screen & must set Google as the default search engine to qualify for any revshare.
Google has a policy of being vague about using clickstream data to influence ranking, though they have heavily relied upon clickstream data to influence ranking. Advances in machine learning have made it easier to score content to where the clickstream data had become less important.
When Apple Maps launched & Google Maps lost the default position on iOS Google Maps lost 60% of their iOS distribution, and that was with how poorly the Apple Maps roll out went.
Google sometimes subverted their typical auction dynamics and would flip the order of the top 2 ads to boost ad revenues.
Google had a policy of "shaking the cushions" to hit the quarterly numbers by changing advertiser ad prices without informing advertisers that they'd be competing in a rigged auction with artificially manipulated shill bids from the auctioneer competing against them.

When Google talked about hitting the quarterly numbers with shaking the cusions the 5% number which was shared skewed a bit low:

For a brand campaign focused on a niche product, she said the average CPC at $11.74 surged to $25.85 over the last six months, amounting to a 108% increase. However, there wasn’t an incremental return on sales.

“The level to which [price manipulations] happens is what we don’t know,” said Yang. “It’s shady business practices because there’s no regulation. They regulate themselves.”

Early in the history of search ads Google blocked trademark keyword bidding. They later allowed it. When keyword bidding on trademarks was allowed it led to a conundrum for some advertisers. If you do not defend your trademark you could lose it, but if you agree with competitors not to bid on each other's trademarks the FTC could come after you - like they did with 1-800 Contacts. This set up forces many brands to participate in auctions where they are arbitraging their own pre-existing brand equity. The ad auctioneer runs shady auctions where it looks across at your account behavior and bids then adjusts bid floors to suck more money out of you. This amounts to something akin to the bid jamming that was done in early Overture, except it is the house itself doing it to you! The last auction I remembered like that was SnapNames, where a criminal named Nelson Brady on the executive team used the handle halverez to leverage participant max bids and put in bids just under their bids. The goal of his fraud? To hit the numbers & get an earn out bonus - similar to how Google insiders were discussing "shaking the cushions" to hit the number.

Halverez created a program which looked across aggregate bid data, join auctions which only had 1 other participant, and then use the one-way view of competing bids to put in a shill bid to drive up costs - which sure sounds conceptually similar to Google's "shaking the cushions."

"Just looking at this very tactically, and sorry to go into this level of detail, but based on where we are I'm afraid it's warranted. We are short __% queries and are ahead on ads launches so are short __% revenue vs. plan. If we don't hit plan, our sales team doesn't get its quota for the second quarter in a row and we miss the street's expectations again, which is not what Ruth signaled to the street so we get punished pretty badly in the market. We are shaking the cushions on launches and have some candidates in May that will help, but if these break in mid-late May we only get half a quarter of impact or less, which means we need __% excess to where we are today and can't do it alone. The Search team is working together with us to accelerate a launch out of a new mobile layout by the end of May that will be very revenue positive (exact numbers still moving), but that still won't be enough. Our best shot at making the quarter is if we get an injection of at least __%, ideally __%, queries ASAP from Chrome. Some folks on our side are running a more detailed, Finance-based, what-if analysis on this and should be done with that in a couple of days, but I expect that these will be the rough numbers.

The question we are all faced with is how badly do we want to hit our numbers this quarter? We need to make this choice ASAP. I care more about revenue than the average person but think we can all agree that for all of our teams trying to live in high cost areas another $___,___ in stock price loss will not be great for morale, not to mention the huge impact on our sales team." - Google VP Jerry Dischler

Google is also pushing advertisers away from keyword-based bidding and toward a portfolio approach of automated bidding called Performance Max, where you give Google your credit card and budget then they bid as they wish. By blending everything into a single soup you may not know where the waste is & it may not be particularly easy to opt out of poorly performing areas. Remember enhanced AdWords campaigns?

Google continues to blur dataflow outside of their ad auctions to try to bring more of the ad spend into their auctions.

Wow. Google. Years behind other browsers (aka monopoly power), Google is attempting to deprecate tracking system A (aka third party cookies) and replace it with another tracking system B (aka Topics) that treats sites as G data mules.

This is deceptive as hell comparing B to A. pic.twitter.com/hCBJgYr7qn— Jason Kint (@jason_kint) September 22, 2023

The amount Google is paying Apple to be the default search provider is staggering.

What is $18 billion / year buying ? The DoJ has narrowed in an agreement not to compete between Apple and Google: "Sanford Bernstein estimates Google will pay Apple between $18 billion and $19 billion this year for default search status" https://t.co/HmoZxCZkqm— Tim Wu (@superwuster) September 22, 2023

Tens of billions of dollars is a huge payday. No way Google would hyper-optimize other aspects of their business (locating data centers near dams, prohibiting use of credit card payments for large advertisers, cutting away ad agency management fees, buying Android, launching Chrome, using broken HTML on YouTube to make it render slowly on Firefox & Microsoft Edge to push Chrome distribution, all the dirty stuff Google did to violate user privacy with overriding Safari cookies, buying DoubleClick, stealing the ad spend from banned publishers rather than rebating it to advertisers, creating a proprietary version of HTML & force ranking it above other results to stop header bidding, & then routing around their internal firewall on display ads to give their house ads the advantage in their ad auctions, etc etc etc) and then just throw over a billion dollars a month needlessly at a syndication partner.

This is right -- Google was once an extraordinary product, but over time became stagnant & too grabby of random revenue as it ate its ecosystem. Makes it the right time to force Google to try and compete without reaching for its bribery checkbook
https://t.co/gDhtDMjfo0— Tim Wu (@superwuster) September 22, 2023

For perspective on the scale of those payments consider that it wasn't that long ago Yahoo! was considered a big player in search and Apollo bought Yahoo! plus AOL from Verizon for about $5 billion & then was quickly able to sell branding & technology rights in Japan to Softbank for $1.6 billion & other miscellaneous assets for nearly a half-billion, reducing the net cost to only $3 billion.

If Google loses this lawsuit and the payments to Apple are declared illegal, that would be a huge revenue (and profit) hit for Apple. Apple would be forced to roll out their own search engine. This would cut away at least 30% of the search market from Google & it would give publishers another distribution channel. Most likely Apple Search would launch with a lower ad density than Google has for short term PR purposes & publishers would have a year or two of enhanced distribution before Apple's ad load matched Google's ad load.

It is hard to overstate how strong Apple's brand is. For many people the cell phone is like a family member. I recently went to upgrade my phone and Apple's local store closed early in the evening at 8pm. The next day when they opened at 10 there was a line to wait in to enter the store, like someone was trying to get concert tickets. Each privacy snafu from Google helps strengthen Apple's relative brand position.

While Google's marketshare is rock solid, the number of search engines available has increased significantly over the past few years. Not only is there Bing and DuckDuckGo but the tail is longer than it was a few years back. In addition to regional players like Baidu and Yandex there's now Brave Search, Mojeek, Qwant, Yep, and You. GigaBlast and Neeva went away, but anything that prohibits selling defaults to a company with over 90% marketshare will likely lead to dozens more players joining the search game. Search traffic will remain lucrative for whoever can capture it, as no matter how much Google tries to obfuscate marketing data the search query reflects the intent of the end user.

Categories:

google

AI-Driven Search

Aaron Wall — Sun, 19 Feb 2023 15:05:34 -0800

I just dusted off the login here to realize I hadn't posted in about a half-year & figured it was time to write another one. ;)

Yandex Source Code Leak

Some of Yandex's old source code was leaked, and few cared about the ranking factors shared in the leak.

Mike King made a series of Tweets on the leak.

I'm gonna take a break, but I've seen a lot of people say "Yandex is not Google."

That's true, but it's still a state of the art search engine and it's using a lot of Google's open source tech like Tensor Flow, BERT, map reduce, and protocol buffers.

Don't sleep on this code.— Mic King (@iPullRank) January 28, 2023

The signals used for ranking included things like link age

Main insights after analysing this list:

#1 Age of links is a ranking factor. pic.twitter.com/U47uWvEq9w— Alex Buraks (@alex_buraks) January 27, 2023

and user click data including visit frequency and dwell time

#8 A lot of ranking factors connected with user behaivor - CTR, last-click, time on site, bounce rate.

Note: I'm 100% sure that in Yandex thouse factors impacting much more than in Google. pic.twitter.com/nBhe5cpPFx— Alex Buraks (@alex_buraks) January 27, 2023

Google came from behind and was eating Yandex's lunch in search in Russia, particularly by leveraging search default bundling in Android. The Russian antitrust regulator nixed that and when that was nixed, Yandex regained strength. Of course the war in Ukraine has made everything crazy in terms of geopolitics. That's one reason almost nobody cared about the Yandex data link. And the other reason is few could probably make sense of understanding what all the signals are or how to influence them.

The complexity of search - when it is a big black box which has big swings 3 or 4 times a year - shifts any successful long term online publishers away from being overly focused on information retrieval and ranking algorithms to focus on the other aspects of publishing which will hopefully paper over SEO issues. Signs of a successful & sustainable website include:

It remains operational even if a major traffic source goes away.
People actively seek it out.
If a major traffic source cuts its distribution people notice & expend more effort to seek it out.

As black box as search is today, it is only going to get worse in the coming years.

ChatGPT Hype

The hype surrounding ChatGPT is hard to miss. Fastest growing user base. Bing integration. A sitting judge using the software to help write documents for the court. And, of course, the get-rich-quick crew is out in full force.

Some enterprising people with specific professional licenses may be able to mint money for a window of time

there will probably be a 12 to 24 month sweet spot for lawyers smart enough to use AI, where they will be able to bill 100x the hours they currently bill, before most of that job pretty much vanishes— Mike Solana (@micsolana) February 7, 2023

but for most people the way to make money with AI will be doing something that AI can not replicate.

It's adorable that people are only slowly realizing that Google search at least fed sites traffic, while chat AI thingies slurp up and summarize content, which they anonymize and feed back, leaving the slurped sites traffic-less and dying. But, innovation.— Paul Kedrosky (@pkedrosky) February 9, 2023

It is, in a way, a tragedy of the commons problem, with no easy way to police "over grazing" of the information commons, leading to automated over-usage and eventual ecosystem collapse.— Paul Kedrosky (@pkedrosky) February 9, 2023

Bing Integration of Open AI Technology

The New Bing integrated OpenAI's ChatGPT technology to allow chat-based search sessions which ingest web content and use it to create something new, giving users direct answers and allowing re-probing for refinements. Microsoft stated the AI features also improved their core rankings outside of the chat model: "Applying AI to core search algorithm. We’ve also applied the AI model to our core Bing search ranking engine, which led to the largest jump in relevance in two decades. With this AI model, even basic search queries are more accurate and more relevant."

Here's a demo of the new #AI-powered @Bing in @MicrosoftEdge, courtesy of @ijustine! pic.twitter.com/xIDjWSHYA0— DataChazGPT (not a bot) (@DataChaz) February 7, 2023

Fawning Coverage

Some of the tech analysis around the AI algorithms is more than a bit absurd. Consider this passage:

the information users input into the system serves as a way to improve the product. Each query serves as a form of feedback. For instance, each ChatGPT answer includes thumbs up and thumbs down buttons. A popup window prompts users to write down the “ideal answer,” helping the software learn from its mistakes.

A long time ago the Google Toolbar had a smiley face and a frown face on it. The signal there was basically pure spam. At one point Matt Cutts mentioned Google would look at things that got a lot of upvotes to see how else they were spamming. Direct Hit was also spammed into oblivion many years before that.

High Confidence, But Often Wrong

There are two other big issues with correcting an oracle.

You'll lose your trust in an oracle when you repeatedly have to correct it.
If you know the oracle is awful in your narrow niche of expertise you probably won't trust it on important issues elsewhere.

Beyond those issues there is the concept of blame or fault. When a search engine returns a menu of options if you pick something that doesn't work you'll probably blame yourself. Whereas if there is only a single answer you'll lay blame on the oracle. In the answer set you'll get a mix of great answers, spam, advocacy, confirmation bias, politically correct censorship, & a backward looking consensus...but you'll get only a single answer at a time & have to know enough background & have enough topical expertise to try to categorize it & understand the parts that were left out.

Creating A Fuzy JPEG

This New Yorker article did a good job explaining the concept of lossy compression:

"The fact that Xerox photocopiers use a lossy compression format instead of a lossless one isn’t, in itself, a problem. The problem is that the photocopiers were degrading the image in a subtle way, in which the compression artifacts weren’t immediately recognizable. If the photocopier simply produced blurry printouts, everyone would know that they weren’t accurate reproductions of the originals. What led to problems was the fact that the photocopier was producing numbers that were readable but incorrect; it made the copies seem accurate when they weren’t. ... If you ask GPT-3 (the large-language model that ChatGPT was built from) to add or subtract a pair of numbers, it almost always responds with the correct answer when the numbers have only two digits. But its accuracy worsens significantly with larger numbers, falling to ten per cent when the numbers have five digits. Most of the correct answers that GPT-3 gives are not found on the Web—there aren’t many Web pages that contain the text “245 + 821,” for example—so it’s not engaged in simple memorization. But, despite ingesting a vast amount of information, it hasn’t been able to derive the principles of arithmetic, either. A close examination of GPT-3’s incorrect answers suggests that it doesn’t carry the “1” when performing arithmetic."

Exciting New Content Farms

Ted Chiang then goes on to explain the punchline ... we are hyping up eHow 2.0:

Even if it is possible to restrict large language models from engaging in fabrication, should we use them to generate Web content? This would make sense only if our goal is to repackage information that’s already available on the Web. Some companies exist to do just that—we usually call them content mills. Perhaps the blurriness of large language models will be useful to them, as a way of avoiding copyright infringement. Generally speaking, though, I’d say that anything that’s good for content mills is not good for people searching for information. The rise of this type of repackaging is what makes it harder for us to find what we’re looking for online right now; the more that text generated by large language models gets published on the Web, the more the Web becomes a blurrier version of itself.

The same New Yorker article mentioned the concept that if the AI was great it should trust its own output as input for making new versions of its own algorithms, but how could it score itself against itself when its own flaws are embedded recursively in layers throughout algorithmic iteration without any source labeling?

Google's AI Strategy

Google fast followed Bing's news with a vapoware announcement of Bard. Some are analyzing Google letting someone else go first as being a sign Google is behind the times and is getting caught out by an upstart.

Google bought DeepMind in 2014 for around $600 million. They've long believed in AI technology, but they haven't been using it to re-represent third party content in the SERPs to the degree Microsoft is now doing in Bing.

My view is Google had to let someone else go first in order to defuse any associated antitrust heat. "Hey, we are just competing, and are trying to stay relevant to change with changing consumer expectations" is an easier sell when someone else goes first. One could argue the piss poor reception to the Bard announcement is actually good for Google in the longterm as it makes them look like they have stronger competition than they do, rather than being a series of overlapping monopoly market positions (in search, web browser, web analytics, mobile operating system, display ads, etc.)

Google may well have major cultural problems, but "They are all the natural consequences of having a money-printing machine called “Ads” that has kept growing relentlessly every year, hiding all other sins. (1) no mission, (2) no urgency, (3) delusions of exceptionalism, (4) mismanagement."

AI = Money / Increased Market Cap

The capital markets are the scorecard for capitalism. It is hard to miss how much the market loved the Bing news for Microsoft & how bad the news was for Google.

Google Stock vs. Microsoft Stock after both AI Presentations: pic.twitter.com/wATkw1pTxj— Ava (AI) (@ArtificialAva) February 8, 2023

Millions Suddenly Excited About Bing

In a couple days over a million people signed up to join a Bing wait list.

We're humbled and energized by the number of people who want to test-drive the new AI-powered Bing! In 48 hours, more than 1 million people have joined the waitlist for our preview. If you would like to join, go to https://t.co/4sjVvMSfJg! pic.twitter.com/9F690OWRDm— Yusuf Mehdi (@yusuf_i_mehdi) February 9, 2023

Your Margin is My Opportunity

Microsoft is pitching this as a margin compression play for Google

$MSFT CEO is declaring war:

"From now on, the [gross margin] of search is going to drop forever...There is such margin in search, which for us is incremental. For Google it’s not, they have to defend it all" [@FT]— The Transcript (@TheTranscript_) February 8, 2023

that may also impact their TAC spend

PREDICTION: Google’s $15B deal with Apple to be the default search on iPhone will be re-negotiated and be a bidding war between MSFT/Bing and Google.

It will become at least $25B, if not more.

If MSFT is willing to spend $10B on OpenAI, they’ll spend even more here.— Alexandr Wang (@alexandr_wang) February 7, 2023

ChatGPT costs around a couple cents per conversation: "Sam, you mentioned in a tweet that ChatGPT is extremely expensive on the order of pennies per query, which is an astronomical cost in tech. SA: Per conversation, not per query."

The other side of potential margin compression comes from requiring additional computing power to deliver results:

Our sources indicate that Google runs ~320,000 search queries per second. Compare this to Google’s Search business segment, which saw revenue of $162.45 billion in 2022, and you get to an average revenue per query of 1.61 cents. From here, Google has to pay for a tremendous amount of overhead from compute and networking for searches, advertising, web crawling, model development, employees, etc. A noteworthy line item in Google’s cost structure is that they paid in the neighborhood of ~$20B to be the default search engine on Apple’s products.

AI is the New Crypto

Since AI is the new crypto, everyone is integrating it, if only in press release format, while banks ban it.

Opera's web browser has a sidebar feature for summarizing articles.
Amazon is including AI integrations in AWS.
Facebook releasing their large language model.
BuzzFeed engineered a short squeeze in their stock by announcing payments from Facebook and that they'd use ChatGPT to generate content. Unsurprisingly their writers were unimpressed and their first topics were madlib quizes. The short squeeze saw the stock pop a couple hundred percent and would have been far more extreme if Comcast hadn't been a big seller. According to FactSet so far this year Comcast has reduced their stake from 24.51% to 15.9%.
AI iced tea coming right up!

And for a cherry on top of the hype cycle:

A gradual transition gives people, policymakers, and institutions time to understand what’s happening, personally experience the benefits and downsides of these systems, adapt our economy, and to put regulation in place. It also allows for society and AI to co-evolve, and for people collectively to figure out what they want while the stakes are relatively low.

We believe that democratized access will also lead to more and better research, decentralized power, more benefits, and a broader set of people contributing new ideas. As our systems get closer to AGI, we are becoming increasingly cautious with the creation and deployment of our models.

We have a nonprofit that governs us and lets us operate for the good of humanity (and can override any for-profit interests), including letting us do things like cancel our equity obligations to shareholders if needed for safety and sponsor the world’s most comprehensive UBI experiment.

Algorithmic Publishing

The algorithms that allow dirt cheap quick rewrites won't be used just by search engines re-representing publisher content, but also by publishers.

After Red Ventures acquired cNet they started publishing AI content. The series of tech articles covering that AI content lasted about a month. In the past it was the sort of coverage which would have led to a manual penalty, but with the current antitrust heat Google can't really afford to shake the boat & prove their market power that way.

Men's Journal also had AI content problems.

Here's why I am very concerned for website owners.https://t.co/RgKrXUocZT is similar to ChatGPT but up to date and conversational.

My bet is that Google's AI Chat will be similar to this but better. If so, while some people will still visit the websites listed, many will not. pic.twitter.com/jWbsTqeveF— Dr. Marie Haynes (@Marie_Haynes) January 30, 2023

AI content poured into a trusted brand monetizes the existing brand equity until people (and algorithms) learn not to trust the brands that have been monetized that way.

A funny sidebar here is the original farmer update that aimed at eHow skipped hitting eHow because so many journalists were writing about how horrible eHow was. Google

New Google Ad Labeling

Aaron Wall — Sat, 15 Oct 2022 17:56:57 -0700

TechCrunch recently highlighted how Google is changing their ad labeling on mobile devices.

A few big changes include:

ad label removed from individual ad units
where the unit-level label was instead becomes a favicon
a "Sponsored" label above ads
the URL will show right of the favicon & now the site title will be in a slightly larger font above the URL

An example of the new layout is here:

Displaying a site title & the favicon will allow advertisers to get brand exposure, even if they don't get the click, while the extra emphasis on site name could lead to shifting of ad clicks away from unbranded sites toward branded sites. It may also cause a lift in clicks on precisely matching domains, though that remains to be seen & likely dependes upon many other factors. The favicon and site name in the ads likely impact consumer recall, which can bleed into organic rankings.

After TechCrunch made the above post a Google spokesperson chimed in with an update

Changes to the appearance of Search ads and ads labeling are the result of rigorous user testing across many different dimensions and methodologies, including user understanding and response, advertiser quality and effectiveness, and overall impact of the Search experience. We’ve been conducting these tests for more than a year to ensure that users can identify the source of their Search ads and where they are coming from, and that paid content is clearly labeled and distinguishable from search results as Google Search continues to evolve

The fact it was pre-announced & tested for so long indicates it is both likely to last a while and will in aggregate shift clicks away from the organic result set to the paid ads.

Categories:

google

Google Helpful Content Update

Aaron Wall — Fri, 19 Aug 2022 01:15:45 -0700

Granular Panda

Reading the tea leaves on the pre-announced Google "helpful content" update rolling out next week & over the next couple weeks in the English language, it sounds like a second and perhaps more granular version of Panda which can take in additional signals, including how unique the page level content is & the language structure on the pages.

Like Panda, the algorithm will update periodically across time & impact websites on a sitewide basis.

Cold Hot Takes

The update hasn't even rolled out yet, but I have seen some write ups which conclude with telling people to use an on-page SEO tool, tweets where people complained about low end affiliate marketing, and gems like a guide suggesting empathy is important yet it has multiple links on how to do x or y "at scale."

Trashing affiliates is a great sales angle for enterprise SEO consultants since the successful indy affiliate often knows more about SEO than they do, the successful affiliate would never become their client, and the corporation that is getting their asses handed to them by an affiliate would like to think this person has the key to re-balance the market in their own favor.

My favorite pre-analysis was a person who specialized in ghostwriting books for CEOs Tweeting that SEO has made the web too inauthentic and too corporate. That guy earned a star & a warm spot in my heart.

Profitable Publishing

Of course everything in publishing is trade offs. That is why CEOs hire ghostwriters to write books for them, hire book launch specialists to manipulate the best seller lists, or even write messaging books in the first place. To some Dan Price was a hero advocating for greater equality and human dignity. To others he was a sort of male feminist superhero, with all the Harvey Weinstein that typically entails.

Anyone who has done 100 interviews with journalists see ones that do their job by the book and aim to inform their readers to the best of their abilities (my experiences with the Wall Street Journal & PBS were aligned with this sort of ideal) and then total hatchet jobs where a journalist plants a quote they want & that they said, that they then attributes it to you (e.g. London Times freelance journalist).

There are many dimensions to publishing:

depth
purpose
timing
audience
language
experience
format
passion
uniqueness
frequency

Blogs to Feeds

For a long time indy blogs punched well above their weight due to the incestuous nature of cross-referencing each other, the speed of publishing when breaking news, and how easy feed readers made it to subscribe to your favorite blogs. Google Reader then ate the feed reader market & shut down. And many bloggers who had unique things to say eventually started to repeat themselves. Or their passions & interests changed. Or their market niche disappeared as markets moved on. Starting over is hard & staying current after the passion fades is difficult. Plus if you were rather successful it is easy to become self absorbed and/or lose the hunger and drive that initially made you successful.

Around the same time blogs started sliding people spent more and more time on various social networks which hyper-optimized the slot machine type dopamine rush people get from refreshing the feed. Social media largely replaced blogs, while legacy media publishers got faster at putting out incomplete news stories to be updated as they gather more news. TikTok is an obvious destination point for that dopamine rush - billions of short pieces of content which can be consumed quickly and shared - where the user engagement metrics for each user are tracked and aggregated across each snippet of media to drive further distribution.

Burnout & Changing Priorities

I know one of the reasons I blog less than I used to is a lot of the things I would write would be repeats. Another big reason was when my wife was pregnant I decided to shut down our membership site so I could take my wife for a decently long walk almost everyday so her health was great when it came time to give birth & ensure I had spare capacity for if anything went wrong with the pregnancy process. As a kid my dad was only around much for a few summers and I wanted to be better than that for my kid.

The other reason I cut back on blogging is at some point search went from a endless blue water market to a zero sum game to a negative sum game (as ad clicks displaced organic clicks). And in such an environment if you have a sustainable competitive advantage it is best to lean into it yourself as hard as you can rather than sharing it with others. Like when we had an office here our link builders I trained were getting awesome unpaid links from high-trust sources for what backed out to about $25 of labor time (and no more than double that after factoring in office equipment, rent, etc.).

If I share that script / process on the blog publicly I would move the economics against myself. At the end of the day business is margins, strategy, market, and efficiency. Any market worth being in is going to have competition, so you need to have some efficiency or strategic differentiators if you are going to have sustainable profit margins. I've paid others many multiples of that for link building for many years back when links were the primary thing driving rankings.

I don't know the business model where sharing the above script earns more than it costs. Does one launch a Substack priced at like $500 or $1,000 a month where they offer a detailed guide a month? How many people adopt the script before the response rates fall & it offsets the costs by more than the revenues? My issue with consulting is I always wanted to over-deliver for clients & always ended up selling myself short when compared to publishing, so I just stick with a few great clients and a bit of this and that vs going too deep & scaling up there. Plus I had friends who went big and then some of their clients who were acquired had the acquirer brag about the SEO, that lead to a penalty, then the acquirer of the client threw the SEO under the bus and had their business torched.

When you have a kid seeing them learn and seeing wonderment in their eyes is as good as life gets, but if you undermine your profit margins you'd also be directly undermining your own child's future ... often to help people who may not even like you anyhow. That is ultimately self defeating as it gets, particularly as politics grow more polarized & many begin to view retribution as a core function of government.

I believe there are no limits to the retributive and malicious use of taxation as a political weapon. I believe there are no limits to the retributive and malicious use of spending as a political reward.

Margins

The role of search engines is to suck as much of the margins as they can out of publishing while trying to put some baseline floor on content quality so that people would still prefer to use a search engine rather than some other reference resource. Google sees memes like "add Reddit to the end of your search for real content" as an attack on their own brand. Google needs periodic large shake ups to reaffirm their importance, maintain narrative control around innovation, and to shake out players with excessive profit margins who were too well aligned with the current local maxima. Google needs aggressive SEO efforts with large profits to have an "or else" career risk to them to help reign in such efforts.

You can see the intent for career risk in how the algorithm will wait months to clear the flag:

Google said the helpful content update system is automated, regularly evaluating content. So the algorithm is constantly looking at your content and assigning scores to it. But that does not mean, that if you fix your content today, your site will recover tomorrow. Google told me there is this validation period, a waiting period, for Google to trust that you really are committed to updating your content and not just updating it today, Google then ranks you better and then you put your content back to the way it was. Google needs you to prove, over several months - yes - several months - that your content is actually helpful in the long run.

If you thought a site were quality, had some issues, the issues were cleaned up, and you were still going to wait to rank it appropriately ... the sole and explicit purpose of that delay is career risk to others to prevent them flying to close to the sun - to drive self regulation out of fear.

Brand counts for a lot in search & so does buying the default placement position - look at how much Google pays Apple to not compete in search, or look at how Google had that illegal ad auction bid rigging gentleman's agreement with Facebook to not compete with a header bidding solution so Google could maintain their outsized profit margins on ad serving on third party websites.

Business ultimately is competition. Does Google serve your ads? What are the prices charged to players on each side of each auction & how much rake can the auctioneer capture for themselves?

The Auctioneer's Shill Bid - Google Halverez (beta)

That is why we see Google embedding more features directly in their search results where they force rank their vertical listings above the organic listings. Their vertical ads are almost always placed above organics & below the text AdWords ads. Such vertical results could be thought of as a category-based shill bid to try to drive attention back upward, or move traffic into a parallel page where there is another chance to show more ads.

This post stated:

Google runs its search engine partly on its internally developed Cloud TPU chips. The chips, which the company also makes available to other organizations through its cloud platform, are specifically optimized for artificial intelligence workloads. Google’s newest Cloud TPU can provide up to 275 teraflops of performance, which is equivalent to 275 trillion computing operations per second.

Now that computing power can be run across:

millions of books Google has indexed
particular publishers Google considers "above board" like Reuters, AP, the New York Times, the Wall Street Journal, etc.
historically archived content from trusted publishers before "optimizing for search" was actually a thing

... and model language usage versus modeling the language usage of publishers known to have weak engagement / satisfaction metrics.

Low end outsourced content & almost good enough AI content will likely tank. Similarly textually unique content which says nothing original or is just slapped together will likely get downranked as well.

Expect Volatility

They would not have pre-announced the update & gave some people some embargoed exclusives unless there was going to be a lot of volatility. As typical with the bigger updates, they will almost certainly roll out multiple other updates sandwiched together to help obfuscate what signals they are using & misdirect people reading too much in the winners and losers lists.

Here are some questions Google asked:

Do you have an existing or intended audience for your business or site that would find the content useful if they came directly to you?
Does your content clearly demonstrate first-hand expertise and a depth of knowledge (for example, expertise that comes from having actually used a product or service, or visiting a place)?
Does your site have a primary purpose or focus?
After reading your content, will someone leave feeling they’ve learned enough about a topic to help achieve their goal?
Will someone reading your content leave feeling like they’ve had a satisfying experience?
Are you keeping in mind our guidance for core updates and for product reviews?

As a person who has ... erm ... put a thumb on the scale for a couple decades now, one can feel the algorithmic signals approximated by the above questions.

To the above questions they added:

Is the content primarily to attract people from search engines, rather than made for humans?
Are you producing lots of content on different topics in hopes that some of it might perform well in search results?
Are you using extensive automation to produce content on many topics?
Are you mainly summarizing what others have to say without adding much value?
Are you writing about things simply because they seem trending and not because you'd write about them otherwise for your existing audience?
Does your content leave readers feeling like they need to search again to get better information from other sources?
Are you writing to a particular word count because you've heard or read that Google has a preferred word count? (No, we don't).
Did you decide to enter some niche topic area without any real expertise, but instead mainly because you thought you'd get search traffic?
Does your content promise to answer a question that actually has no answer, such as suggesting there's a release date for a product, movie, or TV show when one isn't confirmed?

Some of those indicate where Google believes the boundaries of their own role as a publisher are & that you should stay out of their lane. :D

Barrier to Entry vs Personality

One of the interesting things about the broader scope of algorithm shifts is each thing that makes the algorithms more complex, increases barrier to entry, and increases cost ultimately increases the chunk size of competition. And when that is done what is happening is the microparasite is being preference over the microparasite. Conceptually Google has a lot of reasons to have that bias or preference:

fewer entities to police (lower cost)
more data to use to police each entity (higher confidence)
easier to do direct deals with players which can move the needle (more scale)
if markets get too consolidated Google can always launch a vertical service & tip the scale back in the other direction (I see your Amazon ad revenue and I raise you free product listing ads)
the macroparasites have more "sameness" between them (making it easier for Google to create a competitive clone or copy)

So long as Google maintains a monopoly on web search the bias toward macroparasites works for them, as people can not see what they do not see & do not know what does not exist, or what exists but is hidden to them.

I think when people complain about the web being inauthentic what they are really complaining about is the algorithmic choices & publishing shifts that did away with the indy blogs and replaced with with the dopamine feed viral tricks and the same big box scaled players which operate multiple parallel sites to where you are getting the same machinery and content production house behind multiple consecutive listings. They are complaining about the efforts to snuff out the microparasite also scrubbing away personality, joy, love, quirkiness, weirdness, and the stuff you would not typically find on content by factory order websites.

Let's Go With Consensus Here!

The above leads you down well worn paths, rather than the magic of serendipity & a personality worn on your sleeve that turns some people on while turning other people off.

Text which is roughly aligned with a backward looking consensus rather than at the forefront of a field.

If you believe this effort will enhance info literacy, and that it represents evolved search, you're an idiot.

Sharyl Attkisson gave us the head's up that they'd push censorship controls as "media literacy" several years ago.— john andrews (@johnandrews) August 13, 2022

History is written by the victors. Consensus is politically driven, backward looking, and has key messages memory holed.

Did he just say that? Yep. pic.twitter.com/gu9Fk7t1Sv— Kevin Sorbo (@ksorbs) August 18, 2022

Some COVID-19 Fun to "Fact" Check

I spent new years in China before the COVID-19 crisis hit & got sick when I got back. I used so much caffeine the day I moved over a half dozen computers between office buildings while sick. I week later when news on Twitter started leaking of the COVID-19 crisis hit I thought wow this looks even worse than what I just had. In the fullness of time I think I had it before it was a crisis. Everyone in my family got sick and multiple people from the office. Then that COVID-19 crisis news came out & only later when it was showed that comorbidities and the elderly had the worse outcomes did I realize they were likely the same. Then after the crisis had been announced someone else from the office building I was in got it & then one day it was illegal to go into the office. The lockdown where I lived was longer than the original lockdown in Wuhan. Those lockdowns destroyed millions of lives.

The reason the response to the COVID-19 virus was so extreme was huge parts of politically interested parties wanted to stop at nothing to see orange man ejected from the White House. So early on when he blocked flights from China you had prominent people in political circles calling him xenophobic, and then the head of public health in New York City was telling you it was safe to ride the subway and go about your ordinary daily life. That turned out to be deadly partisan hackery & ignorance pitched as enlightenment, leading to her resignation.

Then the virus spreads wildly as one would expect it to. And draconian lockdowns to tank the economy to ensure orange man was gone, mail in voting was widespread, and the election was secured.

I actually appreciate Sam Harris for saying this out loud. This is what the vast majority of the anti Trump crowd believes, but most of them won’t say it. At least when it’s said, you can see it for what it is.pic.twitter.com/NmOqshoZlS— Dave Smith (@ComicDaveSmith) August 18, 2022

Some of the most ridiculous heroes during this period wrote books about being a hero. Andrew "killer" Cuomo had time to write his "did you ever know that I'm your hero" book while he simultaneously ordered senior living homes to take in COVID-19 positive patients. Due to fecal-oral transmission and poor health outcomes for senior citizens sick enough to be in a senior living home his policies lead to the manslaughter of thousands of senior citizens.

You couldn't go to a funeral and say goodbye because you might kill someone else's grandma, but if you were marching for social justice (and ONLY social justice) that stuff was immune to the virus.

Ron DeSantis on public health experts making an exception to lockdowns for George Floyd protests: “That's when I knew these people are a bunch of frauds”

pic.twitter.com/PzjPc80Q3g— Benny Johnson (@bennyjohnson) August 5, 2022

Suggesting looking at the root problems like no dad in the home i

Automating Ourselves Out of Existence

Aaron Wall — Mon, 23 May 2022 08:22:25 -0700

Time has grown more scarce after having a child, so I rarely blog anymore. Though I thought it probably made sense to make at least a quarterly(ish) post so people know I still exist.

One of the big things I have been noticing over the past year or so is an increasing level of automation in ways that are not particularly brilliant. :D

Just from this past week I've had 3 treat encounters on this front.

One marketplace closed my account after I made a bunch of big purchases, likely presuming the purchases were fraudulent based on the volume, new account & an IP address in an emerging market economy. I never asked for a refund or anything like that, but when I believe in something I usually push pretty hard, so I bought a lot. What was dumb about that is they took a person who would have been a whale client & a person they were repeatedly targeting with ads & turned them into a person who would not recommend them ... after being a paying client who spent a lot and had zero specific customer interactions or requests ... an all profit margin client who spent big and then they discarded. Dumb.

Similarly one ad network had my account automatically closed after I had not used it for a while. When I went to reactivate it the person in customer support told me it would be easier to just create a new account as reactivating it would take a half week or more. I said ok, went to set up a new account, and it was auto-banned and they did not disclose why. I asked feedback as to why and they said that they could not offer any but it was permanent and lifetime.

A few months go by and I wondered what was up with that and I logged into my inactive account & set up a subaccount and it worked right away. Weird. But then even there they offer automated suggestions and feedback on improving your account performance and some of them were just not rooted in fact. Worse yet, if they set the default targeting options to overly broad it can cause account issues in a country like Vietnam to where if you click to approve (or even auto approve!) their automated suggestions you then get notifications about how you are violating some sort of ToS or guidelines ... if they can run that logic *after* you activate *their* suggestions, why wouldn't they instead run that logic earlier? How well do they think you will trust & believe in their automated optimization tips if after you follow them you get warning pop overs?

Another big bonus recently was a client was mentioned in a stray spam email. The email wasn't from the client or me, but the fact that a random page on their site was mentioned in a stray spoofed email that got flagged as spam meant that when the ticket notification from the host sent wounded up in spam they never saw it and then the host simply took their site offline. Based on a single email sent from some other server.

Upon calling the host with a friendly WTF they explained to the customer that they had so many customers they have to automate everything. At the same time when it came time to restoring hosting that the client was paying for they suggested the client boot in secure mode, run Apache commands x and y, etc. ... even though they knew the problem was not with the server, but an overmalicious automated response to a stray mention in a singular spam email sent by some third party.

When the host tried to explain that they "have to" automate everything because they have so many customers the customer quickly cut them off with "No, that is a business choice. You could charge different prices or choose to reach out to people who have spent tens of thousands on hosting and have not had any issues in years." He also mentioned how emails can be sent to spam, or be sent to an inbox on the very web host that went offline & was then inaccessible. Then the lovely customer support person stated "I have heard that complaint before" meaning they are aware of the issue, but do not see it as an issue for them. When the customer said they should follow up any emails with an SMS for servers going offline the person said you could do it on your end & then later sent them a 14-page guide for how to integrate the Twillio API.

Nothing in the world is fair. Nothing in the world is equal. But there are smart ways to run a business & dumb ways to run a business.

If you have enough time to write a 14-page integration guide it probably makes sense to just incorporate the feature into the service so the guide is unneeded!

Businesses should treat their heavy spenders or customers with a long history of a clean account with more care than a newly opened account. I had a big hedge fund as a client who would sometimes want rush work done & would do stuff like "hey good job there, throw in an extra $10,000 for yourself as a bonus" on the calls. Whenever they called or emailed they got a quick response. :D

I sort of get that one small marketplace presuming my purchases might have been a scam based on how many I did, how new my account was, and how small they were, but the hosting companies & ad networks that are worth 9 to 12 figures should generally do a bit better. Though in many ways the market cap is a sign the entity is insulated from market pressures & can automate away customer service hoping that their existing base is big enough to offset the customer support horror stories that undermine their brand.

It works.

At least for a while.

A parallel to the above is my Facebook ad account, which was closed about a half decade or so ago due to geographic mismatch. That got removed, but then sort of only half way. If I go to run ads it says that I can't, but then if I go to request an account review to once again explain the geographic difference I can't even get the form to submit unless I edit the HTML of the page on the fly to seed the correct data into the form field as by default it says I can not request a review since I have no ad account.

The flip side of the above is if that level of automation can torch existing paid accounts you have to expect the big data search & social companies are taking a rather skeptical view of new sites or players wanting to rank freely in their organic search results or social feeds. With that being the case, it helps to seed what you can to provide many signals that may remove some of the risks of getting set in the bad pile.

I have seen loads of people have their YouTube or Facebook or whatever such account get torched & only override the automated technocratic persona non grata policies by having followers in another channel who shared their dire situation so it could get flagged for human review and restoration. If that happens to established & widely followed players who have spent years investing into a platform the odds of it happening to most newer sites & players is quite high.

You can play it safe and never say anything interesting, ensuring you are well within the Overtone Window in all aspects of life. That though also almost certainly guarantees failure as it is hard to catch up or build momentum if your defining attribute is being a conformist.

Categories:

internet

Engineering Search Outcomes

Aaron Wall — Wed, 19 Jan 2022 04:49:50 -0800

Kent Walker promotes public policies which advantage the Google monopoly.

His role doing that means he has to write some really bad hot takes that lack context or intentionally & dishonestly redirect attention away from core issues - that's his job.

With that in mind, his most recent blog post defending the Google monopoly was exceptional.

Force Ranking of Inferior Search Results

"When you have an urgent question — like “stroke symptoms” — Google Search could be barred from giving you immediate and clear information, and instead be required to direct you to a mix of low quality results."

On some search queries users get a wall of Google ads, the forced ranked Google insert (or sometimes multiple of them with local & ecommerce) and then there can even be a "people also ask" box above the first organic result.

The idea that organic results must be low quality if not owned & operated indicates 1 of the following 3 must be true:

they should not be in search
their content scraping & various revenue shifting scams with their ad tech stack demonetized legit publishers
their forced rank of their own content is stripping them of the signals needed to rank websites & pages

Whenever Google puts a "people also ask" box above the first organic result that is them saying they did not know what to rank, or they are just trying to create a visual block to push the organic result set down the page and user attention back up toward the ads.

The solution to Google's claims is easy to solve. Either of the following would work.

Have an API that allows user choice (to set rich snippet or vertical defaults in various categories), or
If the vertical inserts remain Google-only then for Google to justify force ranking their own results above the organic result set Google should also be required to rank those same results above all of their ads, so that Google is demonetizing Google along with the rest of the ecosystem, rather than just demonetizing third parties.

If the thesis that this information needs to be front and center & that is a matter of life or death, then asking searchers to first scroll past a page or two of ads is not particularly legitimate.

Spam & Security

"when you use Google Search or Google Play, we might have to give equal prominence to a raft of spammy and low-quality services."

Many of the worst versions of spam that have repeatedly made news headlines like fake tech support, fake government document providers, and fake locksmiths were buying distribution through Google Ads or were featured in the search results through Google force ranking their own local search offering even though they knew the results were vastly inferior to Yelp.

If Google did not force rank Google local results above the rest of the organic result set then the fake locksmiths would not have ranked.

I have lost count of how many articles I have read about hundreds or thousands of fake apps in the Google Play store which existed to defraud advertisers or commit identity theft, but there have been literally thousands of such articles. I see a similar headline at least once a month without eve looking for them. Here is one this week for scammers monetizing the popularity of Wordle with fake apps.

Making matters worse, some of the tech support scams showed the URL of a real business and rerouted the call through a Google number directly to a scammer. A searcher who trusted Google & sees Apple.com or Dell.com on Google Ads in the search results then got connected with a scammer who would commit identity theft or encrypt their computer then demand ransom cryptocurrency payments to decrypt it.

After making the ads harder to run for scammers Google decided the problem was too hard & expensive to sort out so they also blocked legitimate computer repair shops.

Sometimes Google considers something spam strictly due to financial considerations.

Their old remote rater documents stated *HELPFUL* hotel affiliate websites should be labeled as spam.

Years later the big OTAs are complaining about Google eating their lunch as well as Google is twice as big as the next player.

At one point Google got busted for helping an advertiser route around the automated safety features built into their ad network so that they could pay Google to run ads promoting illegal steroids.

With cartels, you can only buy illegal goods and services from the cartel if you don't want to suffer ill consequences. The same appears to be true here.

The China Problem

"Handicapping America’s technology leaders would threaten our leading sources of research and development spending — just as bipartisan voices in Congress are recognizing the need to increase American R&D investment to stay competitive in the global race for AI, quantum, and other advanced technologies."

We are patriotic, and, but China... is a favorite misdirection of a tech monopolist.

The problem with that is while Eric Schmidt warns it is a national emergency if China overtakes the US in AI tech, Google also operates an AI tech lab in China.

In other words, Eric Schmidt is trying to warn you about himself and his business interests at Google.

Duplicitous? Absolutely.

Patriotic? Less than Chamath!

Who the fuck did this? pic.twitter.com/BD4NKpila6— Girolamo Carlo Casio (Free Twatter) (@INArteCarloDoss) January 19, 2022

Inflation

"the online services targeted by these bills have reduced prices; these bills say nothing about sectors where prices have actually been rising and contributing to inflation."

Technology is no doubt deflationary (moving bits on an optical line is cheaper than printing out a book and shipping it across the world) BUT some dominant channels have increased the cost of distribution by increasing the chunk size of information and withholding performance information.

Before Google Analytics was "free" there was a rich and vibrant set of competition in web analytics software with lots of innovation from players like ClickTracks.

Most competing solutions went away.

Google moved away from an installed licensing model to a hosted service where they can change the price upon contract renewal.

Search hid progressively more performance information over time, only sampled data from larger data sets, & now you can sign up for Google Analytics 360 starting at only $150,000 per year.

The hidden search performance data also has many layers to that onion. Not only does Google not show keyword referrers on organic search, but they often don't show your paid search keywords either, and they keep extending out keyword targeting broader than advertisers intend.

Yesterday's announcement on match type changes had me crawling through query data this morning. I'm staring at many 2-3 word exact match keywords that are matching to 8-word queries. G thinks 'deck paint' and 'how do i put paint on my deck' mean the exact same thing. CPA is 10x.— Brad Geddes (@bgtheory) February 5, 2021

Google used to pay Brad Geddes to run official Google AdWords ad training seminars for advertisers, so the idea that *he* has to express his frustrations on Twitter is an indication of how little effort Google is putting into having open communications channels or caring about what their advertisers think.

This is in accordance with the Google customer service philosophy:

he told her that the whole idea of customer support was ridiculous. Rather than assuming the unscalable task of answering users one by one, Page said, Google should enable users to answer one another's questions.

Those who were paying for ads get the above "serve yourself" treatment, all the while Google regularly resets user default ad settings to extend out ad distribution, automatically ad keywords, shift to enhanced AdWords ad campaigns, etc.

Then there are other features which would be beneficial and offered in a competitive market that have been deprioritized. Many years ago eBay did a study which showed their branded Google AdWords ad buys were cannibalistic to eBay profits. Google maintained most advertisers could not conduct such a study because it would be too expensive and Google does not make the feature set available as part of their ad suite.

Missing Information

"When you search for local businesses, Google Search and Maps may be prohibited from highlighting information we gather about hours of operation, contact information, and reviews. That could hurt small businesses and local retailers, as well as their customers."

Claiming reviews or an attempt to offer a comprehensive set of accurate review data as a strong point would be economical with the truth.

Back when I had a local business page my only review was from a locksmith spammer / scammer who praised his own two businesses, trashed a dozen other local locksmiths, crapped on a couple local SEO services, and joked about how a local mover smashed the guts out of his dog. Scammer fake reviewer's name was rather sophisticated ... it was ... Loop Dee Loop

About a decade back when Google was clearly losing Google took Yelp reviews wholesale (sometimes without even attributing them to Yelp!) and told Yelp that if they did not want Google stealing their work and displacing them with a copy of it then they should block GoogleBot. Google offered the same sort of advice / threat to TripAdvisor.

A few years before that Google temporarily "forgot" to show phone numbers on local listings.

After Yelp turned down an acquisition offer by Google & Yelp did a great job making some people aware of how Google was stealing their reviews wholesale without attribution Google bought Zagat & Fromer's to augment the Google local review data and then sold those businesses off.

This is sort of the same playbook Google has run in the past elsewhere. After Groupon said no to Google's acquisition offer, Google quickly provided daily deal ads to over a dozen Groupon competitors to help commoditize the Groupon offering and market position.

Ultimately with the above sort of stuff Google is primarily a volume aggregator or has lower editorial costs than pure plays due to the ability to force bundle their own distribution. And they use the ability to rank themselves above a neutral algorithmic position as a core part of their biz dev strategy. When shopping search engines were popular Google kept rewording the question set they sent remote raters to justify rank demotion for shopping search engines & Google also came up with innovative ranking "signals" like concurrent ranking of their own vertical search offering whenever competitors x or y are shown in the result set & rolled out a "diversity" algorithm to limit how many comparison shopping sites could appear in the search results. The intent of the change was strictly anti-competitive:

"Although Google originally sought to demote all comparison shopping websites, after Google raters provided negative feedback to such a widespread demotion, Google implemented the current iteration of its so-called 'diversity' algorithm."

As a matter of fact, part of one of many document dumps in recent years went further than the old concurrent ranking signal to a rank x above y feature which highlights how YouTube can be hard coded at a number 1 ranking position.

Part of that guide highlighted how to hardcode ranking YouTube #1.

If you re-represent content & can force rank yourself #1 (with larger listings) that can be used to force other players onto your platform on your terms. Back when YouTube was must less of a sure thing Google suggested they could threaten to change copyright.

This same approach to "relevancy" is everywhere.

Did you watermark your images? Well shame on you, as that is good for a rank demotion

And if there are photos which are deemed illegal Google will make you file an endless series of DMCA removal requests even though they already had the image fingerprinted.

Now there are some issues where there is missing information. These areas involve original reporting on local politics & are called news deserts. As the ad pie has consolidated around Google & Facebook that has left many newspapers high and dry.

Private equity players like Alden Global Capital buy up newspapers, fire journalists, and monetize brand equity as they drive the papers into the ground.

If you are sub-scale maybe Google steals your money or hits you with a false positive algorithm flag that has you seeking professional mental health help.

Big players get a slower blood letting.

Google has maintained they do not make any money from news search, but the states lawsuit around ad tech made it clear Google promoted AMP for anti-competitive purposes to block header bidding, lied to news publishers to get them to adopt AMP and eat the tech costs of implementation, did a deal with their biggest competitor in online advertising Facebook to maintain the status quo, charge over double what their competitors do for ad tech, and had a variety of bid rigging auction manipulation algorithms they used to keep funneling more money to themselves.

Internally they had an OKR to make *most* search clicks land on AMP pages within a year of launch

"AMP launched as an open source project in October 2015, with 26 publishers and over 40 publications already publishing AMP files for our preview demo. Our team built g.co/ampdemo and is now racing towards launching it for all of our users. We're responsible for the AMP @ Google integrations, particularly focusing on Search, our most visible product. We have a Google-wide 2016 OKR to deliver! By the end of 2016, our goal is that 50%+ of content consumed through Search is being consumed through AMP."

You don't get over half the web to shift to a proprietary version of HTML in under a year without a lot of manipulation.

So, when Google tells buyers an ad sold for one price and they tell sellers it sold for a lower price, isn't that just plain old fraud? I mean, on top of the anti-competitive tying and all that, fraud is illegal, isn't it?— Jerry Neumann (@ganeumann) January 14, 2022

Categories:

google

Cannibalization

Tom Capper — Fri, 17 Sep 2021 00:00:00 -0700

In today's episode of Whiteboard Friday, Moz SEO expert Tom Capper walks you through cannibalization: what it is, how to identify it, and how to fix it.

Tackling 8,000 Title Tag Rewrites: A Case Study

Dr. Peter J. Meyers — Thu, 16 Sep 2021 00:00:00 -0700

Let's take an in-depth look at Moz.com title tags that were re-written by Google, including three case studies where we managed to fix bad rewrites.

How Our Website Conversion Strategy Increased Business Inquiries by 37%

Irwin Hau — Wed, 15 Sep 2021 00:00:00 -0700

See how, through several little tweaks to their conversion strategy, the team at Chromatix attracted a higher tier of customers, more inquiries, plus over $780,000 worth of new sales opportunities.

How to Add Products to Your Google My Business Listing, Illustrated

Miriam Ellis — Mon, 13 Sep 2021 00:00:00 -0700

Miriam helps you get started in Google My Business Products with this illustrated tutorial, walking you through how to add your most important products and services.

The Three Bosses of SEO

Ola King — Fri, 10 Sep 2021 00:00:00 -0700

For SEO, there are three main “bosses”, with different needs: your business, your searchers, and your search engines. How do you answer to all of them?

Winning the Page Speed Race: How to Turn Your Clunker of a Website Into a Race Car

Pam Aungst Cronin — Wed, 08 Sep 2021 00:00:00 -0700

Winning the page speed race requires the same things as winning a car race: making sure that your vehicle is as lightweight as possible, as powerful as possible, and that you navigate the racetrack as efficiently as possible.

Responsive Search Ads: 5 Best Practices for Google Ads PPC Search Campaigns

Tanuja Mahdavi — Tue, 07 Sep 2021 00:00:00 -0700

These tips will help you optimize your responsive search ads in your Google Ads search campaigns, and increase clicks and conversions.

How to Calculate Your SEO ROI Using Google Analytics

Adriana Stein — Mon, 06 Sep 2021 00:00:00 -0700

Measuring ROI for your SEO efforts involves two factors: KPIs and the cost of your current SEO campaigns. With GA, you can pinpoint where your audience is coming from, set goals to stay on track, and incorporate the most attractive keywords to rank better in search engines.

How to Use STAT to Find SEO Opportunities at Scale

Cyrus Shepard — Fri, 03 Sep 2021 00:00:00 -0700

Today, Cyrus explains how powerful STAT can be when you’re trying to discover SEO opportunities on a massive scale.

The Guide to Targeted-Impact Link Building

Garrett French — Wed, 01 Sep 2021 00:00:00 -0700

Links drive rankings — that’s one thing that SEOs and marketers can agree on. But which rankings, and for which pages on your website? Use this guide to build links that impact rankings for specific pages on your website.

Jasper.ai Review

Aaron Wall — Fri, 30 Apr 2021 08:46:10 -0700

Background / Intro

One of my longtime friends who was Internet marketing long before I was hit me up on Skype about a week ago praising Jasper.ai. I have to think long and hard about any other time he has really pitched or recommended something like that & really I just can't think of any other time where he did that. The following day my wife Giovanna mentioned something to me and I was like "oh you should check out this thing my buddy recommended yesterday" and then I looked and realized they were both talking about the same thing. :D

I have a general heuristic that if people I trust recommend things I put them near the top of the "to do" list and if multiple people I trust do that I pull out the credit card and run at it.

Unfortunately I have been a bit burned out recently and launched a new site which I have put a few hundred hours into, so I haven't had the time to do too much testing, BUT I have a writer who works for me who has a master's degree in writing, and figured she could do a solid review. And she did. :D

She is maybe even a bit more cynical than I am (is that even possible?) and a certified cat lady who loves writing, reading, poetry and is more into a soft sell versus aggressive sales.

Full disclosure...the above link and the one at the end of this post are affiliate links, but they had zero impact on the shape or format of the review. The reviewer was completely disconnected from the affiliate program and I pulled out my credit card to pay for the software for her to test it out.

With that tiny bit of a micro-introduction, the rest of the post from here on out is hers. I may have made a couple minor edits for clarity (and probably introduced a few errors she will choke me for. :D) but otherwise the rest of this post is all her ...

An In-depth Review of the Conversion.ai Writing Software

Considering the possibilities of artificial intelligence (AI), we picture robots doing tasks autonomously like humans. With a computer’s brain power, productivity is accelerated significantly. We also expect AI programs to have the capability to evolve intelligently the longer they are used. These types of AI employ “machine learning,” or deep learning to solve problems.

AI technology can be leveraged by various industries, especially with writing. Recently, I learned about the Conversion.ai copywriting tool. It uses machine learning which claims to write “high converting copy” for websites, ads, landing pages, emails, etc. The software is geared towards writers, marketers, entrepreneurs, and agencies that benefit from creating engaging and effective copy. To date, companies such as Hubspot, Shopify, and Salesforce are known to use the software. Currently, it’s offering a 7-day free trial with 20,000-word credits.

To give you the lowdown on Conversion.ai, I wrote an in-depth review of how this software works. I’ll go through its various features and show examples of how I used them. I’ll include the advantages of using Conversion.ai’s Jasper (that’s what it’s called) in writing scenarios. More importantly, I’ll discuss challenges and specific limitations this tool might present.

Assistance in Creating High Conversion Copy

As a writer doing web copy for 10 years, including the time I took a post-grad creative writing degree, I grabbed the opportunity to try this AI software. For starters, it struck me how Conversion.ai claims to provide “high converting copy” for increased conversion and higher ROI. Such claims are a tall order. If you’ve been in the marketing or sales industry, you’d know conversion depends on so many other factors, such as the quality of the actual product, customer support, price, etc. It’s not just how well copy is written, though it’s a vital part. But anyway, upon more research, I learned the app generates copy based on proven high conversion sales and marketing messages.

To be honest, I have mixed feelings about this conversion strategy. I believe it’s a double-edged sword. This is not to undermine facts or measurable data. Basing content creation on “proven content” means you’re likely using the same phrases, techniques, and styles already used by successful competitors. This serves as a jumping board for ideas of course, so you know what’s already there. However, it can be an echo chamber. Marketers must not forget that execution must still be fresh. Otherwise, you’ll sound like everyone else.

Next, while it seems sustainable, it also sounds pretty safe. If your product or service is not that distinct, you must put extra effort to create content that stands out. This applies to all aspects of the marketing strategy, not just in writing content. It’s a crucial principal I learned after reading Purple Cow by Seth Godin (thanks for the book suggestion, Aaron!).

Depending on your product or service, Conversion.ai will generate copy that most consumers keep going back to. Based on the samples it generated, I’d say it really does come up with engaging copy, though it needs editing. If your business must rewrite product descriptions for extensive inventories, Conversion.ai can cut the time in half. It can help automate description rewriting without hiring more writers. That saves money and time, so businesses need fewer writers and editors.

What did I learn? Conversion.ai can make writing and editing faster, yes, especially for low-level content focused on descriptions. It can also inform the strength of your ideas for more creative campaigns. However, it still takes solid direction and creativity to drive good marketing copy forward. That said, it’s only as good as the writer utilizing this app. As a content creator, you cannot rely on it solely for creativity. But as an enhancer, it will significantly help push ideas forward, organize campaigns, and structure engaging copy effectively.

When you use this app, it offers many different features that help create and organize content. It also customizes copy for various media platforms. Beyond rewriting , it even has special brainstorming tools designed to help writers consider various idea angles. This can add more flavor and uniqueness into a campaign.

At the end of the day, what will set your copy apart is the strength of your ideas and your communication strategy. How you customize content for a business is still entirely up to you. AI writing tools like Conversion.ai can only help enhance your content and the ideas behind it. It’s a far cry from creating truly unique concepts for your campaign, but it definitely helps.

Conversion.ai Writing Features & How They Work

This AI writing app comes with plenty of “writing templates” that are customized to help you write with a specific framework or media platform in mind. Currently, Conversion.ai offers 39 different writing templates or content building blocks that deliver results. We’ll provide details for how each one works.

For company or product descriptions, Conversion.ai has a Start Here step by step guide, which says users should alternate between the Product Description and the Content Improver template until they have found the right mix they’re looking for. But for this review, I just focused on how to use the templates for different writing projects. The app comes with video instructions as well as a live training call if you need further assistance on how to use it.

Each template asks you to input a description or what you want to write about. This is limited to 600 characters. Writing the description is the sole basis for how Jasper will generate ways to write or expand your content. It also helps you brainstorm and structure ideas for an article or campaign.

But as an issue, I find the 600-character limit can hinder reposting the full content generated by the AI back into the template for improvement. Yes, it churns out marketing copy of more than 600 characters. If you want to post the improved copy again, you might have to do this in two batches. In any case, Jasper can generate as many improved writing samples as you need.

To give you a better idea, here are different Conversion.ai templates and how they work. This is going to take a while, so have your coffee ready.

Long-form Assistant

This is for longer articles, emails, scripts, and stories. It’s also suggested for writing books. It has two modes, a blank document where you can start typing freely and an assistant workflow. The blank document also lets you access the rest of the other writing templates vertically. On the other hand, the long-form assistant workflow is where the app asks you to describe the content you want to create. Consider this carefully. The better you can articulate your topic, the higher quality content Jasper can help generate.

For the example, suppose I want to write about what it took to finally release Zack Synder’s 2021 Justice League. I want to write this feature article for my film and culture website.

Jasper asks for a maximum of three keywords. It’s optional, but I presume adding keywords will help Jasper generate more relevant content. Next, it prompts you to write a working title and start an introductory paragraph. Once you write your initial title, it will generate other title ideas.

For the title, I wrote: The Challenges of Releasing Zach Snyder’s Justice League 2021
It generated the following suggestions:

Jasper generated a long list of appropriate and catchy titles. I personally liked “The Tumultuous Journey of Zack Snyder’s Justice League 2021,” though I’d shorten it a bit. I also liked “The Darkest, Toughest Production in Film History,” which basically tells audiences how hard it was to produce the version of the film. Though it’s an exaggeration, it can be qualified in the article. The other suggestions with “Behind the Scenes” and “Towards a Better Script” were more specific angles. I like that I could explore those topics too. Generally, I think it’s definitely a great tool to make title writing faster.

So far, so good, right? But when I got to content suggestions, it got a bit messy. It was mainly because the suggested content was too general. It also tended toward suggesting expansions that were incoherent to the main topic. This did not sound very promising. Moreover, the AI added bits of information such as dates and other related information. I had to check if these details were used accurately. In a previous test I did (and even for this example), it completely got a date wrong. So I advise writers to always double check the details suggested by Jasper.

Take a look below. The top paragraph was the one I wrote, while the ones below are suggested by Jasper.

Content suggestions from Jasper:

1) You might not be able to see Zack Snyder’s Justice League on the big screen, but you can catch it online in 2021. It was released digitally by Warner Bros. on November 27th 2020 and we’ve been watching it slowly climb the ranks of IMDB since then. The film had a troubled production between 2016 and 2017 with the script going through major changes before and during shooting. But now that all is said and done, what did people think? Let’s find out!

2) Justice League is a film that was released on November 17, 2017. The movie had been preceded by Batman v Superman: Dawn of Justice and Wonder Woman. It’s also the fifth installment in the DC Extended Universe (DCEU). Despite being generally well-received by critics, it was considered to be a disappointment at the box office. In this blog post, we’ll take you behind the scenes and show you what went wrong with Zack Snyder’s 2021 Justice League film production!

3) Director Zack Snyder’s Justice League film was one of the most anticipated films of 2017. Unfortunately, the film had a troubled production and was not released until 2021. That didn’t stop it from becoming one of the highest-grossing films of all time. What does this have to do with SEO? When you release content on your website, be sure to include keywords that are relevant to your business and industry!

At first glance, the introduction actually looks appealing to Justice League fans. Many people have been anticipating it on the big screen. But upon further reading, compared to the paragraph I wrote, the AI content had so many problems. Besides being too general, it had issues with imprecise details. Though you can argue these problems are small and editable, it adds time to your work. It can even derail you from focusing on your topic.

The first AI suggestion wrote that Snyder Cut was released digitally by Warner Bros. in November 27, 2020. Upon further research, I found no such confirmation of this. However, there was a YouTube video “speculating” it’s release in November 2020. But from the looks of it, this did not pan out. Officially, Zack Snyder’s Justice League was released in March 18, 2021 by HBO Max via streaming platform, according to Rotten Tomatoes. And yes, it has been climbing the ranks since its digital release.

If you’re not careful about fact-checking, you might end up with misleading information. And frankly, I feel as if some of the other suggestions may tend towards fluff. However, what you can do is choose the best suggestions and put them together into one coherent paragraph. The first suggestion ended the introduction with “But now that all is said and done, what did people think? Let’s find out!” While it’s something I want to touch on eventually, it is not the main focus of my introduction. The AI was not sensitive enough to sense this follow up was out of place. I’d rather get to the details of the challenging production. If I use this suggestion, I’ll have to edit it into “Let’s take a look at what it took to deliver the highly anticipated Snyder Cut,” or something to that effect.

The second example, on the other hand, was quite a miss. It started by talking about the 2017 Justice League film. While it’s good to expound on the history of the project started, it got lost in discussing the 2017 version. Worse, it did not transition the topic smoothly into the 2021 Snyder Cut. If I read this introduction, I’d be confused into thinking the article was about the 2017 Justice League. Finally, it awkwardly ended the paragraph with “we’ll take you behind the scenes and show you what went wrong with Zack Snyder’s 2021 Justice League film production!” Besides the wordy sentence, suddenly it’s talking about the 2021 Justice League out of nowhere. I would not phrase the production’s challenges as something that went wrong. That’s unnecessary hype. It’s confusing, and just an example of bad writing. Again, while it can be fixed with editing, I feel better off writing on my own.

Finally, the third example actually started okay. But then it started talking about SEO out of nowhere. I don’t know where that came from or why the AI did that, but I’ll count it as a totally unusable suggestion from the app. I reckon there might be more of those glitches if I generate more content suggestions from Jasper.

SIDEBAR FROM AARON: COUGH. SEO IS EVERYTHING. HOW DO I REEEEECH DEZ KIDZ

I noticed these were nuances the AI was not able to catch. It’s probably even based on trending articles at the time, which had a tendency towards hype and dated showbiz information. And though the suggestions were interesting, they were mostly too general or against the direction I needed. If the usage of the information is not accurate, imagine what that would mean for health or political articles. But too be fair, it did generate other usable suggestions with less serious edits. It’s worth looking into those.

However, by this time, I felt I was better off writing the feature without the app, at least for this example. I guess it’s really a hit or miss. Even with so many content suggestions, I think you can still end up with inappropriate samples even if you find good ones. But at least you got a good title already. Personally, I’d rather go straight to researching on my own.

Framework Templates

Conversion.ai allows you to write copy based on marketing frameworks that have been used by professionals for years. It’s ideal for brands, products, and services you need to promote. This features includes the following templates:

AIDA Framework: The AIDA template stands for Attention, Interest, Desire, and Action. This basically divides your copy into sections drawing attention from consumers and piquing their interest. The suggested copy also includes content that appeals to the consumer’s desire, then ends with a call to action.
PAS Framework: The PAS template is structured by generating copy which highlights the consumer’s Problem, Agitate, and Solution. It’s focused on how a particular product will help solve a consumer’s problem.
Bridge-After-Bridge Framework: Also known as BAB framework, this copywriting structure revolves around the idea of getting a consumer from a bad place to a better one. It shows the before and after scenario after benefitting from a product.

For this example, I used the AIDA template for an imagined non-invasive weight loss service company. The new company promotes fitness and advocates against fad diets. It performs non-surgical weight loss procedures, such as wraps and thermomagnetic massages.

Again, Jasper asks for a description. It also requires you to specify the tone of the copy. I placed “friendly” and “professional” under the box. See my input below.

Here’s the first suggestion from Jasper:

Based on this example, I’d say the AI-generated content is quite engaging. It tried to have a personal touch by letting the customer know they’re here to help. The writing empathizes with consumers who have a hard time losing weight. However, since this is for a new company, the introduction “We have helped thousands of people lose weight and get in shape,” does not apply. So as a writer, I simply have to remove it. This can be replaced with the intent to help more people lose weight and get in shape.

I actually pulled out at least 6 different content suggestions. From these, writers could get the best parts and edit them into one strong copy description. On it’s own, the content would still benefit from a lot of editing. Here are some issues you might encounter while generating copy suggestions:

Hard Sell Copy. The sample content can be hard sell, even if you specify a professional tone of voice. It tends to use exclamation marks (!) per sample. I believe this depends on the product or service you are writing about. Certain products or services may sell more with the hard sell approach, so the AI suggests this strategy. It may also appear like the “proven” way to communicate to consumers. But if you’re going against this direction, it’s a nuance the AI tool might miss. If your business or client specifically avoids exclamation marks your copy, be ready to make the necessary edits.
Can be Wordy, Long, Redundant. In terms of style, here’s where you can’t rely on Jasper to write the entire thing. If you happen to input a long and detailed product description, the AI has a tendency to generate wordy variations of the copy. If you notice, some details are also redundant. In copywriting standards, this needs tightening. Conciseness can be an issue, most notably if you’re not used to brevity. Thus, I believe this tool will best benefit writers and editors who have considerable experience in crafting straightforward copy.

Product Description

The app comes with a special template for creating product descriptions. If you have a large inventory of product information for rewriting, this is the right tool to use. It even comes with an optional language output translation feature, which is available in other templates too.

However, the language feature is limited. I tried putting Thai, Italian, and Japanese and it generated few suggestions, some mixed with English. Same thing with Punjabi and Vietnamese. In other templates, they just keep making English suggestions. Filipino is also not recognized by the AI, which likely means it cannot translate a bunch of other languages. This feature obviously needs development. But it’s not the main feature, so I doubt they’ll d

SEMrush IPO (SEMR)

Aaron Wall — Sat, 27 Mar 2021 09:19:22 -0700

On Wednesday SEMrush priced their IPO at $14 a share & listed Thursday.

There have been many marketing and online advertising companies which are publicly traded, but few that were so focused specifically on SEO while having a sizeable market cap. According to this SeekingAlpha post at the IPO price SEMrush had a valuation of about $1.95 to $1.99 billion. For comparison sake, here are some other companies & valuations.

Facebook acquired Instagram for $1 billion.
Google acquired YouTube for $1.65 billion.
Yelp trades at around a $2.9 billion market cap.
Yahoo! was acquired by Verizon for $4.48 billion.
Hubspot has a market cap of around $20.4 billion.

A couple years ago Gannett bought AdWords reseller WordStream. A few years before that they bought ReachLocal. The Hearst publishing empire also bought iCrossing long ago. Marin Software remains publicly traded, but they are only valued at about $20 million.

Newspapers reselling Google AdWords ads isn't really SEO though. Beyond those sorts of deals, many of the publicly traded SEO stuff has been only tangentially relevant to SEO, or crap.

There are some quality category-leading publishers which use SEO as a means of distribution but are not necessarily an SEO service provider like TripAdvisor, BankRate, and WebMD. Over time many of these sorts of companies have been gobbled up by Red Ventures or various private equity firms. Zillow, Yelp and TripAdvisor are some of the few examples which still exist as independent companies.

So that puts most of the publicly traded SEO stuff in one of the following categories...

small scale - does anyone other than Andy Beal & Mike Grehan still remember KeywordRanking / WebSourced / Think Interactive / MarketSmart Interactive?
hope and nope - sites like Business.com were repeatedly acquired but never really gained lasting relevance.
affiliate networks - which reliant on partners with SEO traffic like Quinstreet & Commission Junction. many affiliate networks were hit hard as the barrier to entry in SEO increased over the years. Quinstreet is doing well in some verticals but sold their education division to Education Dynamics for $20 million. CJ was part of the Publicis Groupe acquisition of Epsilon.
pump and dump scams - Demand Media, owner of eHow, which later rebranded as Leaf Group & still trades at a small fraction of their IPO price.

The one lasting counter-example to the above is Barry Diller's IAC. His innovation ecosystem is surreal. Across time & across markets he is the best creator of vertical leading properties later spun off as their own companies. He's owned Expedia, TripAdvisor, LendingTree, HomeAdvisor, Match.com, TicketMaster and so many other category leaders. His buying of Ask.com did not pan out as well as hoped as web browsers turned the address bar into a search box, his ability to differentiate the service went away after they shut down the engine in 2008, he was locked out of mobile search marketshare by default placement contracts & Google pushes back against extension bundling, but just about everything else he touched turned to gold. A lot of their current market cap is their ownership of Vimeo, which by itself is valued at $6 billion.

What is the most recent big bet for Barry Diller? MGM. Last August he bet $1 billion on the growth of online gambling. And he was willing to bet another billion to help them acquire Entain:

IAC has to date invested approximately US$1 billion in MGM with an initial investment thesis of accelerating MGM’s penetration of the $450 billion global gaming market. IAC notes in its letter of intent that IAC continues to strongly support this objective for MGM whether or not a transaction with Entain is consummated.

Barry Diller not accurately projects future trends, but he also has the ability to rehab broken companies past their due dates.

The New York Times bought About.com for $410 million in 2005 & did little with it as its relevance declined over time as its content got stale, Wikipedia grew and search engines kept putting more scraped content in the search results. The relentless growth of Wikipedia and Google launching "universal search" in 2007 diminished the value of About.com even as web usage was exploding.

IAC bought About.com from the New York Times for $300 million in August of 2012. They tried to grow it through improving usability, content depth and content quality but ultimately decided to blow it up.

They were bold enough to break it into vertical category branded sites. They've done amazingly well with it and in many cases they rank 2, 3, 4 times in the SERPs with different properties like TheSpruce, TheBalance, Investopedia, etc. As newspapers chains keep consolidating or going under, IAC is one of the few constant "always wins" online publishers.

At its peak TheBalance was getting roughly 2/3 the traffic About.com generated.

Part of the decline in the chart there was perhaps a Panda hit, but the reason traffic never fully recovered is they broke some of these category sites into niche sites using sub-brands.

All the above search traffic estimate trend charts are from SEMrush. :)

I could do a blog post titled 1001 ways to use SEMrush if you would like me to, though I haven't yet as I already have affiliate ads for them here and don't want to come across as a shill by overpromoting a tool I love & use regularly.

I tend to sort of "not get" a lot of SaaS stocks in terms of prices and multiples, though they seem to go to infinity and beyond more often than not. I actually like SEMrush more than most though & think they'll do well for years to come. I get the sense with both them and Ahrefs that they were started by programmers who learned marketing rather than started by marketers who cobbled together offerings which they though would sell. If you ever have feedback on ways to improve SEMrush they are fast at integrating it, or at least were in the past whenever I had feedback.

When SEMrush released their S-1 Dan Barker did a quick analysis on Twitter.

Some stats from the S-1: $144 million in annual recurring revenues @ 50% compound annual growth rate, 76% gross margins, nearly 1,000 employees and over 67,000 paying customers.

SEMrush, the SEO tool, has filed to go public. Here's the S-1: https://t.co/i1meSHts4Y

They spent $54 million on marketing last year, for revenue of $125 million.

(gross profit $95m, net loss $7m) pic.twitter.com/iz5nybcwfA— dan barker (@danbarker) March 1, 2021

At some point a lot of tool suits tend to overlap because much of their data either comes from scraping Google or crawling the open web. If something is strong enough of a point of differentiation to where it is widely talked about or marketed then competitors will try to clone it. Thus spending a bit extra on marketing to ensure you have the brand awareness to be the first tool people try is wise. Years ago when I ran a membership site here I paid to license the ability to syndicate some SEMrush data for our members & I have promoted them as an affiliate for what seems like a decade now.

When Dan Baker did his analysis of the S-1 it made me think SEMrush likely has brighter prospects than many would consider. A few of the reasons I could think of off the top of my head:

each day their archive of historical data is larger, especially when you consider they crawl many foreign markets which some other competitive research tools ignore
increasing ad prices promote SEO by making it relatively cheaper
keyword not provided on organic search means third party competitive analysis tools are valuable not only for measuring competitors but also measuring your own site
Google Ads has recently started broadening ad targeting further and hiding some keyword data so advertisers are paying for clicks where they are not even aware what the keyword was

That last point speaks to Google's dominance over the search ecosystem. But it is also so absurd that even people who ran AdWords training workshops point out the absurdity.

Yesterday's announcement on match type changes had me crawling through query data this morning. I'm staring at many 2-3 word exact match keywords that are matching to 8-word queries. G thinks 'deck paint' and 'how do i put paint on my deck' mean the exact same thing. CPA is 10x.— Brad Geddes (@bgtheory) February 5, 2021

In Google maximizing their income some nuance is lost for the advertiser who must dig into N-Gram analysis or look at historical data to find patterns to adjust:

The account overall has a CPA in the $450 range. If the word ‘how’ is in the query, our CPA is over double. If someone searches for ‘quote,’ our CPA is under $300. If they ask a question about cost, the CPA is over $1000. Obviously, looking for quotes versus cost data is very different in the eyes of a user, but not in the matching search terms of Google.

Every ad network has incentive to overstate its contribution to awareness and conversions so that more ad budget is allocated to them.

Facebook kept having to restate their ad stats around video impressions, user reach, etc.
Facebook gave themselves a 28 day window for credit for some app installs.
Google AMP accidentally double counted unique users on Google Analytics (drives adoption = good).
Google Analytics came with last click attribution, which over-credits the search channel you use near the end of a conversion journey.

There are a lot of Google water carriers who suggest any and all of their actions are at worst benevolent, but when I hear about hiding keyword data I am reminded of the following quote from the Texas AG Google lawsuit.

"Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own."

That lawsuit details the great lengths Google went to in order to leverage their search monopoly to keep monopoly profit margins on their display ad serving business.

AMP was created with the explicit intent to kill header bidding as header bidding shifted power and profit margins to publishers. Some publishers saw a 50% rise in ad revenues from header bidding.

Remember how Google made companywide bonuses depend on the performance of the Google Facebook clone named Google+? Google later literally partnered with Facebook on a secret ad deal to prevent Facebook from launching a header bidding solution. The partnership agreement with Facebook explicitly mentioned antitrust repeatedly.

Bid-rigging?! Is this bid-rigging? As in, one of the "supreme evils of antitrust"? As in, the thing that if RE investors do it at foreclosure auctions they go to prison? pic.twitter.com/w7ez6gwfZd— John Newman (@johnmarknewman) December 16, 2020

When a company partners with its biggest direct competitor on a bid rigging scheme you can count on it that the intent is to screw others.

So when you see Google talk about benevolence, remember that they promise to no longer lie in the future & only deceive others into working against themselves via other coercive measures.

We went from the observation that you can't copyright facts to promoting opinion instead:

The Internet commoditized the distribution of facts. The "news" media responded by pivoting wholesale into opinions and entertainment.— Naval (@naval) May 26, 2016

to where after many thousands of journalists have been laid off now the "newspaper of record" is promoting ponzi scheme garbage as a performance art piece:

The NYT made a NFT!

My new column is about NFTs, and I also turned the column into a NFT and put it up for auction on @withFND, with proceeds going to charity.

Bid away, and you could own the first NFT in the paper's 170-year history. https://t.co/9ItGZvID8B— Kevin Roose (@kevinroose) March 24, 2021

The decline of About.com was literally going to be terminal without the work of Barry Diller to revive it. That slide reflected how over time a greater share of searches never actually leave Google:

Of those 5.1T searches, 33.59% resulted in clicks on organic search results. 1.59% resulted in clicks on paid search results. The remaining 64.82% completed a search without a direct, follow-up click to another web property. Searches resulting in a click are much higher on desktop devices (50.75% organic CTR, 2.78% paid CTR). Zero-click searches are much higher on mobile devices (77.22%)

The data from the above study came from SimilarWeb, which is another online marketing competitive research tool planning on going public soon.

Google "debunked" Rand's take by focusing on absolute numbers instead of relative numbers. But if you keep buying default placements in a monopoly ecosystem where everyday more people have access to a computer in their pocket you would expect your marketshare and absolute numbers to increase even if the section of pie other publishers becomes a smaller slice of a bigger pie.

Google's take there is disingenuous at the core. It reminds me of the time when they put out a study claiming brand bidding was beneficial and that it was too complex and expensive for advertisers to set up a scientific study, without any mention of the fact the reason that would be complex and expensive is because Google chooses not to provide those features in their ad offering. That parallels the way they now decide to hide keyword data even from paying advertisers in much the same way they hide ad fees and lie to publishers to protect their ad income.

Google suggests they don't make money from news searches, but if they control most of the display ads technology stack & used search to ram AMP down publishers throats as a technological forced sunk cost while screwing third party ad networks and news publishers, Google can both be technically true in their statement and lying in spirit.

"Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own."

There are many more treats in store for publishers.

Google will stop supporting third party cookies in Chrome next year. They are also going to stop selling ads where targeting is based on tracking user data across websites:

"Google plans to stop selling ads based on individuals’ browsing across multiple websites, a change that could hasten upheaval in the digital advertising industry. The Alphabet Inc. company said Wednesday that it plans next year to stop using or investing in tracking technologies that uniquely identify web users as they move from site to site across the internet. ... Google had already announced last year that it would remove the most widely used such tracking technology, called third-party cookies, in 2022. But now the company is saying it won’t build alternative tracking technologies, or use those being developed by other entities, to replace third-party cookies for its own ad-buying tools. ... Google says its announcement on Wednesday doesn’t cover its ad tools and unique identifiers for mobile apps, just for websites."

Google stated they would make no replacement for the equivalent of the third party cookie tracking of individual users:

"we continue to get questions about whether Google will join others in the ad tech industry who plan to replace third-party cookies with alternative user-level identifiers. Today, we’re making explicit that once third-party cookies are phased out, we will not build alternate identifiers to track individuals as they browse across the web, nor will we use them in our products. We realize this means other providers may offer a level of user identity for ad tracking across the web that we will not — like PII graphs based on people’s email addresses. We don’t believe these solutions will meet rising consumer expectations for privacy, nor will they stand up to rapidly evolving regulatory restrictions, and therefore aren’t a sustainable long term investment."

On the above announcement, other ad networks tanked, with TheTradeDesk falling 20% in two days.

These are all Google's competitors in advertising technology, collapsing after Google announce

The Wrong People Won

Aaron Wall — Wed, 27 Jan 2021 20:01:31 -0800

My initial attraction toward SEO and the web was largely that it was like a new and parallel world that bypassed many traditional gatekeepers.

I wrote an ebook which originally had inconsistent formatting and it was riddled with spelling and grammar errors. I learned to write by writing poorly and often while reading great writers daily.

Ultimately it did not matter that my efforts were subpar on some fronts as few people read early copies, and I was receptive to feedback on how to improve it and rapidly did.

The above process ... growing while few people see your ugly work ... is actually one of the advantages of *NOT* taking venture capital. You get to learn at your own pace while risks are low and only really lean into something when you know it is working. You keep making small bets that won't kill you and then when something works better than you expect you can *REALLY* lean into it.

I ultimately did that with SEO, blogging, and a couple other areas I can't mention too much as I had partners on some projects.

This blog never even started as its own site. It was a section on a different site that was spun out to become its own site when it was obvious blogs were being algorithmically over-promoted due to the cross linking from other bloggers and the instant exposure RSS feeds offered.

Instead of begging a book publisher to publish a book I had a higher margin product and the book publishers were begging me. The market was inverted and an outcast won by bypassing traditional gatekeepers.

When SEO was easy it was the same sort of deal. As long as you tried to learn about what the algorithms valued & put effort behind it you could rank for almost anything.

Early on that meant begging, buying, or borrowing links any way you could. If a project was throwing off big money you'd try public relations and to get high quality links to help reinforce the position and increase its longevity. But even junky links worked fantastic back in the day. That's part of why there was so much blog comment spam, referrer spam, expired domains, cheeseball web directories which actually had pagerank in the URL, article directories, private blog networks, all sorts of other paid links like Text-Link-Ads.com, etc. etc. etc.

New channels provide new opportunities. Small players prove the model, drive adoption, and then over time the affiliate or independent publisher is replaced by some big publisher or a scrape-n-displace offering from the central market operators.

If you take a broad enough view of the world the above sort of water cycle repeatedly happens across all media formats and channels.

New channels emerge
Smaller players and hobbyists are attracted to the new and shiny object
Limited competition & regulation
Channel grows wildly
Channel locked down by regulation or a monopoly

When the channels are new they have the greatest chance of failure, but the biggest potential rewards for early adopters.

As channels are established and competition increases almost all the profit margins get handed over to the central market operator. Everything gets adjust on an "as needed" basis. Anything that hands too much of the profits over to a third party publisher gets cloned by the central network operator, becomes against the terms of service, or is algorithmically or manually neutralized by the central market operators.

affiliates used to be able to sit at the end of the conversion funnel and extract profits from the most valuable keywords, but new algorithmic signals make it hard to stay competitive with limited value add, differentiation, or brand building
commercial keywords are all ads in the search results above the fold & many brands feel the need to bid on their pre-existing brand equity for defensive purposes
Google hid keyword data from organic search & later started to hide some from paid search campaigns as well.
the Chrome browser by default only allows extensions to be downloaded from their official store & while Google got a lot of Chrome distribution through negative option bundling on Flash security updates, they prohibit app bundling in their app store
Apple's iOS and Google Android allow the central network operators to track third party app usage. The Apple Appstore and Google Play have mandatory 30% rakes and may disallow certain widely used apps after those features have been baked into the operating system or cloned and default bundled on new phones.
YouTube takes a 45% revenue share rake & the ad inventory is sold exclusively through Google tools where Google takes up to another 20% rake off the top
Amazon uses your sales data and product design to create what amounts to an effective clone job of it (going so far as to say there are fake safety issues to demand to see where it was manufactured) and then you are forced to bid on your own brand as Amazon gives itself free ads on your brand for their product clone job
Google and Facebook try to suck content into their networks via Instant Articles and AMP. Google gives AMP priority placement in their search results (just like they did previously with Google+, Google Checkout, Google Base / Google Shopping / YouTube / etc etc etc).
Rather than competing, Google and Facebook partnered to illegally bid rig auctions to destroy header bidding & preserve monopoly profit margins, keeping control over external publishers. Google also pushes "privacy" obfuscation which harms third party publishers and third party ad networks while bypassing those firewalls for its own ad network. They are also looking to use their web browser to do away with cookies, further kneecapping other ad networks.
Early Pinterest Ads sent users offsite and often cost only a couple cents a visit while all the internal cross promotion & viral spread across Pinterest was effectively free. Then over time advertisers start getting charged for pins even being opened and getting a user to actually leave Pinterest and click through can cost $5 or $10 a click. Long after I saw Reddit threads about how I was a washed up hack who could not compete in the modern market I literally used Pinterest to seed the growth of a site which now gets about a million organic search visits a month. I recently tried further promoting that site on Pinterest in some new areas, but the economics no longer works for that particular site on that channel.

If you play by the rules suggested by private market participants you are betting that they won't dramatically change their ecosystem at the drop of a hat and they won't compete against you.

And that bet is a REALLY bad bet.

Networks do not stay on top & in control by stagnating. They change with society & if they are influential enough they also change the structure of society.

The Texas AG lawsuit of Google for manipulating the online display ad market lays bare how power works:

Google employees agreed that, in the future, they should not directly lie to publishers, but instead find ways to convince publishers to act against their interest and remove header bidding on their own.

I could easily write a 100 page blog post on that lawsuit while feeling guilty for leaving many things out.

For example, did you know Google stole AdSense earnings from publishers in the AdTrader ad network and lied about refunding that money to advertisers as AdTrader also managed some of the advertiser accounts which got a $0.00 rebate:

We confirmed through multiple sources, both within and outside of Google, through our Google invoices, and data collected from Google APIs that Google never actually refunded any of the confiscated publisher earnings to the advertisers. In fact, Google’s own support team admitted that they never had a system in place for such refunds.

Google is the network I have studied most and know the most about, though others certainly know Facebook equally well. All the large networks growth the predacious exploits.

Even with limited Facebook usage I know they have at various points in time promoted: games, hype headline fake news, lists and viral quiz junk from Buzzfeed, real actual news sites, the Instant Articles version of real actual news, live video, friend content, etc. Facebook also bought Onavo, a VPN network to track the growth of competing apps. That data was used to inform their WhatsApp purchase. And they could see which features from what external networks they should clone, like when Instagram copied much of SnapChat's offering.

You can follow the Facebook terms of service in everything you do, but the odds of that delivering you real and sustainable profit streams is low.

"You can be unethical and still be legal that’s the way I live my life" - Mark Zuckerberg

Few publishers will be experts at both optimizing for the flaw or overpromotion in the current algorithm or network set up AND being good at reinventing themselves to appeal to the algorithms of tomorrow. You ultimately want to use some of any excess profits to build a destination people seek out so you are less dependent on the central network operators.

At the same time, if you ignore the algorithms and just hope for the best you are probably going to lose to a competitor who clones most of your strategy AND manipulates the result set.

You sort of have to figure out what is being over-promoted today AND then try to figure out what will matter tomorrow, while reinvesting profits to the point you are no longer really faking it until you make it.

Realizing that all success is temporary is vital to encourage yourself to take advantage of the opportunities in front of you, while also ensuring you have a plan B in place that acts as a bridge to tomorrow in case your primary channel bombs.

Almost all profit margins (particularly for newer players lacking access to connections, massive cashflows, strong legacy brands, etc.) come from operating somewhere in the gray area. Behave in a manner that is legal, but push the boundaries of terms from other players.

Google funded eHow. Demand Media was ultimately a pump and dump operation. Those who followed it late got their asses handed to them, but those who got in early had plenty of profits they could reinvest in other lower risk ventures. At one point Mahalo publicly listed their page-level earnings data. One of my buddies went through and put that keyword list through TextBroker and uploaded a few hundred articles to an old blog. After about a year that led to a free house for one of their family members. :D

Now Google has far more data to use so it is hard to be anywhere near as exploitative or lowbrow as an eHow or a Mahalo was and expect that stuff to back out.

When Matt Cutts was on TWIG in 2013 he stated:

If you want to stop spam, the most straight forward way to do it is to deny people money because they care about the money and that should be their end goal. But if you really want to stop spam, it is a little bit mean, but what you want to do, is break their spirits. There are parts of Google algorithms specifically designed to frustrate spammers. Some of the things we do is give people a hint their site will drop and then a week or two later, their site actually does drop. So they get a little bit more frustrated. So hopefully, and we’ve seen this happen, people step away from the dark side and say, you know what, that was so much pain and anguish and frustration, let’s just stay on the high road from now on.
...
Some of the stuff I like best is when people say "you know what, this SEO stuff is too unpredictable, I am just going to write some apps."

This past year is the year when "writing some apps" was revealed to have the same core problems that SEO has. Central market operators grabbing their tithings (fight between Apple and entities like Spotify and Epic Games, Google Play pushing through similar 30% rake requirements) and then outright banning apps like Parler from their app stores.

The COVID-19 pandemic moved everyone and everything online.

The ad money follows the attention stream. If the central network operators pay creators nothing then those creators who have a following will find other ways to monetize. Cygnus was early to SEO and he was early to influencer marketing.

Selling a sliver of attention and then using that funds flow to improve website usability, website design, content quality, brand awareness, reach, etc. ... is usually going to work out better for most people than trying to raise venture capital. Many small bets and incremental improvements yields much higher odds of success than a few really big bets.

Speaking of bets, I follow the stock market a bit because it teaches a lot about human psychology, markets and marketing.

Well before the COVID-19 crisis happened the repo market froze. In fact, the Federal Reserve was discussing alternative ways to fund the market's liquidity without looking like they were directly subsidizing and bailing out hedge funds:

the new approach could also create political problems for policy makers, analysts said. The problem centers on the central bank lending directly to hedge funds, the little-regulated investment vehicles that tend to serve wealthy or institutional investors. ... Though hedge funds are key participants in the market—where they both borrow and lend cash—lending to them directly through the FICC would raise questions about whether the government was backstopping their bets, analysts said.

When the COVID-19 crisis happened optics no longer mattered. Bailouts ensued. Without them levered hedge funds were screwed as many instruments became illiquid and spreads blew out even in bedrock stable markets:

Of particular concern: The hedge funds were using trading strategies similar to those employed by Long-Term Capital Management, a fund that collapsed in 1998 and nearly caused a financial meltdown. The bet that hedge funds were making earlier this year was simple enough. Called a basis trade, it involved exploiting a price difference in the Treasury market, generally by selling Treasury futures contracts — promises to deliver a bond or note at a set price on a set date — and buying the comparatively cheap underlying securities.

Toward the end of last year and early this year Bitcoin was a rocket ship on the thesis of mass money printing leading to currency debasement and revaluing finite alternatives to fiat cash upward.

And then regulators began dropping hints while banks started to put the breaks on it. And XRP got kicked hard by the SEC, leading to delisting.

Tether may be an absolute scam (it's hard to short Patio11's knowledge), but in spite of that there are a lot of retail traders bored at home chasing anything that moves. There are ETFs like GBTC sucking up a huge share of the Bitcoin float with no intent of ever liquidating any of the position.

If sports and society shut down and people are stuck in their homes gambling is an unsurprising source of entertainment. Barstool Sports founder David Portnoy got this and quickly became a day trader when he didn't have any sports to talk about. :D

Above I mentioned a bit how the Federal Reserve was ultimately bailing out hedge funds. In an easy money market where central banks are printing tons of money what a lot of hedge funds do is buy higher beta growth names while shorting lower beta value stocks, particularly if they feel those companies are destined to go under.

In some cases the short bets believe ideas from a category apply to a specific company in a way they do not. And that can lead to a massive short squeeze, especially if the company announces a buyback and/or insiders buy.

In other cases, the shorts are so confident in their position, they go HOG WILD with low interest leverage and literally short the entire float of a company, trying to drive it into bankruptcy.

Recently Melvin Capital and some other well-connected hedge funds went short GameStop's stock and a Subreddit named WallStreetBets took the other side of that position.

GME has a 52-week low of $2.57. After being pumped by the Subreddit the stock closed today at $347.51, leading to billions in losses for hedge funds which shorted over 100% of the stock.

According to @S3Partners, short sellers lost $14.3 billion on $GME stock today... just today.— Riley de León (@RileyCNBC) January 27, 2021

The hedge funds that shorted over 100% of a stock ... were market manipulators aiming to manipulate a market.

When they win, that is capitalism.

When they lose, they get bailed out, contact regulators and have pressure applied to prevent THE WRONG PEOPLE from winning.

There are over 2.6 million Wall Street Bet users and only 10,000 hedge funds. The power of the proletariat is now!— Reddit Investors (@redditinvestors) January 27, 2021

The SEC published a statement on market volatility, the Biden administration mentioned it was watching GameStop, Nasdaq's CEO suggested halting trading to allow hedge funds to steamroll Reddit users, the Discord group for WallStreetBets was shut down, and Reddit (at least temporarily) banned the WallStreetBets subreddit for hate speech.

That WallStreetBets was temporarily nuked will likely make the degenerate gamblers even more aggressive.

Emergency Press Conference - The Suits Shut Down @wallstreetbets @WSBChairman My prediction is tomorrow will be intergalactic for $amc $gme $nok

(Im not a financial adviser. Don’t listen to me) pic.twitter.com/oYrsPOz8Vx— Dave Portnoy (@stoolpresidente) January 28, 2021

You can see a lot of moves comin

Apple Search

Aaron Wall — Thu, 27 Aug 2020 22:43:34 -0700

Google, Google, Google

For well over a decade Google has dominated search to where most stories in the search sphere were about Google or something on the periphery.

In 2019 Google generated $134.81 billion in ad revenues.

When Verizon bought core Yahoo three years ago the final purchase price was $4.48 billion. That amount was to own their finance vertical, news vertical, web portal, homepage, email & web search. It also included a variety of other services like Tumblr.

Part of what keeps Google so dominant in search is their brand awareness. That is also augmented by distribution as defaults in Chrome and Android. Then when it comes to buying search distribution from other players like Mozilla Firefox, Opera or Apple's Safari they can outbid everyone else as they are much better at monetizing tier 2 markets and emerging markets than other search companies are since they have such strong ad depth. Even if Bing gave a 100% revshare to Apple they still could not compete with Google in most markets in terms of search monetization.

Apple as a Huge Search Traffic Driver

In 2019 Google paid just under £1.2 billion in default payments for UK search traffic. Most of that went to Apple. Historically when Google broke out their search revenues by region typically the US was around 45% to 46% of search ad revenue & the UK was around 11% to 12%, so it is likely Google is spending north of $10 billion a year to be the default search provider on Apple devices:

Apple submitted that search engines do not pay Apple for the right to be set as the primary default search engine on its devices. However, our assessment is that Google does pay to be the primary default on Apple devices. The agreement between Google and Apple states that Google will be the default web search provider and the same agreement states that Google will pay Apple a specified share of search advertising revenues. We also note that Google does not pay compensation to any partners that set Google Search as a secondary option. This further suggests that Google’s payment to Apple is in return for Apple setting Google as the primary default.

Apple is glad to cash those checks & let Google handle the core algorithmic search function in the web browser, but Apple also auto-completes many searches from within the address bar via various features like website history, top hit, news, Siri suggested website, suggested sites, etc.

A Unique Voice in Search

The nice thing about Apple powering some of those search auto-complete results themselves is their results are not simply a re-hash of the Google search results so they can add a unique voice to the search marketplace where if your site isn't doing as well in Google it could still be promoted by Apple based on other factors.

High-traffic Shortcuts

Apple users generally have plenty of disposable personal income and a tendency to dispose of much of it, so if you are an Android user it is probably worth having an Apple device to see what they are recommending for core terms in your client's markets. If you want to see recommendations for a particular country you may need to have a specialized router targeted to that country or use a web proxy or VPN.

Most users likely conduct full search queries and click through to listings from the Google search result page, but over time the search autocomplete feature that recommends previously viewed websites and other sites likely picks up incremental share of voice.

A friend of mine from the UK runs a local site and the following shows how the Apple ecosystem drove nearly 2/3 of his website traffic.

His website is only a couple years old, so it doesn't get a ton of traffic from other sources yet. As of now his site does not have great Google rankings, but even if it did the boost by the Apple recommendations still provides a tailwind of free distribution and awareness (for however long it lasts).

For topics covered in news or repeat navigational searches Apple likely sends a lot of direct visits via their URL auto-completion features, but they do not use the feature broadly into the tail of search across other verticals, so it is a limited set of searches that ultimately benefit from the shortcuts.

Apple Search Ranking Factors

Apple recently updated their search page offering information about Applebot:

Apple Search may take the following into account when ranking web search results:

Aggregated user engagement with search results

Relevancy and matching of search terms to webpage topics and content

Number and quality of links from other pages on the web

User location based signals (approximate data)

Webpage design characteristics

Search results may use the above factors with no (pre-determined) importance of ranking. Users of Search are subject to the privacy policy in Siri Suggestions, Search & Privacy.

I have seen some country-code TLDs do well in their local markets in spite of not necessarily being associated with large brands. Sites which do not rank well in Google can still end up in the mix provided the user experience is clean, the site is useful and it is easy for Apple to associate the site with a related keyword.

Panda-like Quality Updates

Markets like news change every day as the news changes, but I think Apple also does some Panda-like updates roughly quarterly where they do a broad refresh of what they recommend generally. As part of those updates sites which were once recommended can end up seeing the recommendation go away (especially if user experience declined since the initial recommendation via an ad heavy layout or similar) while other sites that have good engagement metrics get recommended on related searches.

A friend had a website they sort of forgot that was recommended by Apple. That site saw a big jump on July 9, 2018 then it slid back in early August that year, likely after the testing data showed it wasn't as good as some other site Apple recommended. They noticed the spike in traffic & improved the site a bit. In early October it was widely recommended once again. That lasted until May of 2019 when it fell off a cliff once more. They had monetized the site with a somewhat spammy ad network & the recommendation mostly went away.

The recommendations happen as the person types and they may be different for searches where there is a space between keywords and the word is ran together. It is also worth noting Apple will typically recommend the www. version of a site over the m. version of a site for sites that offer both, so it makes sense to ensure if you used separate URLs that the www version also uses a responsive website design.

Indirect Impact on Google

While the Apple search shortcuts bypass Google search & thus do not create direct user signals to impact Google search, people who own an iPhone then search on a Windows computer at work or a Windows laptop at home might remember the site they liked from their iPhone and search for it once more, giving the site some awareness that could indirectly bleed over into impacting Google's search rankings.

Apple could also eventually roll out their own fully featured search engine.

Categories:

other search engines

Overcoming Webmaster Depression

Aaron Wall — Thu, 13 Aug 2020 04:17:16 -0700

This year is a rather easy year to be depressed. ;)

COVID-19, fearmongering media, polarized hyper-charged social media, mass unemployment, lockdowns that killed exercise routines and social connections, loss of hope / purpose / meaning, a guy who stuck a gun in the belly area of a pregnant woman overdosing on fentanyl shortly after he passed counterfeit currency, that broader background being utterly ignored so outrage could fuel widespread rioting with a man in dreadlocks kicking a man sitting in the street unconscious & other bonus random drive by shootings where actual heroes are murdered at random, cities being burned down, communist anarchy, social "justice" movements founded on the idiotic idea of improving society by ripping apart the family unit, etc.

This post is not a suicide letter, but an ode to reality of accepting today for what it is. :D

pic.twitter.com/OWBHGa5eKR— Zero Gravity Media (@zerogravityhxp) August 12, 2020

Last year was the first year where I managed an office with a bunch of employees in it. When the office opened my email inbox had under 2,000 emails built up in it over a 16 year period of working on the web. Far from inbox zero, I am now above 20,000. I think in a Bill Gates interview about a half year ago I smiled after hearing his sort of EGT was how his email inbox was doing. I timed that office opening almost perfectly for COVID-19 so I could have all the stress and cost associated with training a team, setting up a ton of computers, creating workflow, ... and then none of the benefits as the office would get shut down shortly after things began to operate smoothly. :D

By the end of last year a was a bit (err...lot) on the fat side from working too much, too much stress, and exercising too little. My weight and the length of my fuse are reciprocals.

In the past I used to harness negative energy into a form of rage to fuel drive, but now that I am over 40 I find it much harder to live that way. I've already had a number of near death experiences (including one when my wife was pregnant with our only child) and think at some point living that rage-drive way is just shitty. Just say no to endless rage.

So when it was obvious this year was largely going to be dog crap, I started to look internally instead of externally & figured it made more sense to improve health & mood than to fight the gravity of the global depression we are currently living through.

Exogenous Shocks

When things change out of nowhere they can end up dramatically changing the social and economic order.

Many such changes are utterly arbitrary and orthogonal to the concepts of fairness, justice, human decency, etc.

Some parties are politically connected & shielded from actual market forces.

As a self-employed person living overseas I am certainly not one of those protected parties. That said, my family and the people who work for me look to me and hope I can help shield them from some of the crap reality served up this year.

As a rule, when exogenous shocks happen those who are not politically connected get screwed hardest.

Smaller firms tend to under-perform larger firms: "As the earnings season draws to a close, companies within the Russell 2000 stock index — the small-cap benchmark — have reported an aggregate loss of $1.1bn, compared to profits of almost $18bn a year earlier, according to data provider FactSet. Meantime, the much bigger companies within the benchmark S&P 500 index have posted a 34 per cent aggregate drop in earnings, to $233bn."

Poorer people are more likely to lose their jobs.

Emerging markets tend to get hit harder than developed markets. Which only adds to the powder keg of instability as the food price inflation tied to falling incomes makes many people rather desperate.

etc.

As people get desperate violence increases & many governments get overthrown.

Central banks printing cash to prop up the financial markets only increases the divide further.

Congratulations @federalreserve pic.twitter.com/8HxhLH9il5— Sven Henrich (@NorthmanTrader) August 17, 2020

That increased income & wealth inequality makes "the system" only feel that much more fraudulent, which in turn acts as a powder keg to fuel more arbitrary misdirected violence.

Tesla now has a $340 billion market capitalization. They remain unprofitable outside of harvesting tax credits.

Beyond fueling increased violence, the sky high numbers for FOMO stocks also lead some people to feel like they are failures for only slightly succeeding or just getting by.

Others pile in to trashy cryptocurrencies in an attempt to catch up where they only further compound their losses.

Waiting Things Out

It is worth noting many of the jobs that are gone are gone for good.

We may very well be facing a global depression:

"The pandemic has created a massive economic contraction that will be followed by a financial crisis in many parts of the globe, as nonperforming corporate loans accumulate alongside bankruptcies. Sovereign defaults in the developing world are also poised to spike. This crisis will follow a path similar to the one the last crisis took, except worse, commensurate with the scale and scope of the collapse in global economic activity. And the crisis will hit lower-income households and countries harder than their wealthier counterparts. ... In all of the worst financial crises since the mid-nineteenth century, it took an average of eight years for per capita GDP to return to the pre-crisis level. (The median was seven years.) ... The last time all engines failed was in the Great Depression; the collapse this time will be similarly abrupt and steep."

If you can't afford to feed your family of course you have to solve that problem first. But if you are not absolutely financially desperate then this can be a good year to win in ways other than finances & only worry about money after other things are in a better place.

This is a good year to find meaning through various types of self-improvement and doing lots of small & kind things for the people around you. Yesterday was a good day to buy your wife flowers. So is today. Tomorrow is a good day to buy a friend a surprise gift.

One of the best books you can read about developing positive personal habits is Charles Duhigg's The Power of Habit. It is 8 years old now but it is still a great read.

Pushing for broad structural changes in a crisis through ideology which removes ordinary feedback loops often ends up creating only further injustice with the campaign "hero" looking like their polar opposite. Ideology pushed hard enough wraps around to the other side.

When things are absolutely screwed the world over it is better to focus on improving yourself and your family rather than promoting arbitrary extrajudicial justice and burning things down further.

Here are the steps I took to improve a good bit so far this year.

Coronavirus Lockdowns

When I saw a video of a guy walking down the street in Wuhan cough blood and fall over dead I immediately ordered facemasks for everyone in my extended family. I also bought facemasks and gloves into the office for workers. As it turns out gloves were largely a non-winner because using them is more likely to spread virus and bacteria, but the intent was good.

Cygnus recommended taking the supplement quercetin & so did Dr. Zev, so I do that.

Our government does not want us to treat covid early. If I get covid and no hcq access-I would take IMMEDIATELY quercetin 500mg three times a day for 7 days and elemental zinc 50mg one a day for 7 days, and z-pack. Every American home should have quercetin and zinc.— Dr. Zev Zelenko (@zev_dr) August 16, 2020

When lockdowns were announced I hoarded months worth of baby formula so I know my daughter would be ok & bought her a couple birthday presents in case the lockdowns were extended repeatedly. They were, so that worked out ok.

When lockdowns ended I bought a ton of different toys for my daughter so I could share them with her and make up for the limited outside contact for the time being. I also brought my lead graphic & web designer a dual monitor computer to his house to improve his efficiency.

Any day where there is not a lockdown I try to make the most of it knowing another couple months or quarter year can disappear arbitrarily.

Making the most out of the day for me often means doing something positive on the health front & meaning front right away. Things like getting food for my daughter or going for a walk are big wins early in the day as we tend to slow down and get tired as the day drags on.

Health / Fitness

Early in the year when I could use the gym I was walking at a brisk pace for about an hour a day while reading books and listening to podcasts.

After gyms were forced to be closed I started walking outside. Initially this was often to get groceries or various baby supplies, though I continued to walk daily even when there wasn't a real direct need just to keep mood up with all the ridiculous crap going on in the world. I used to think the Philippines was way too hot when I had to drive everywhere, but even if it is hot as hell it isn't bad to be out in the sun and heat so long as you are only walking especially if the walk has a purpose which helps your loved ones in some way.

Walking regularly with nothing else going on can be boring as hell, of course, so to offset the boredom I bring my iPhone and have some Airpod Pro earbuds with their killer noise canceling features. When nobody is near me I sometimes pull down my face mask and jog or sprint for a while to add variety to the day. I also sometimes make people's ears bleed by singing along in an effort to share the joy of whatever I am listening to. :D

There are many awesome acoustic songs on YouTube. Revisiting unheard versions of songs you liked a long time ago can make the lyrics more powerful.

Some of the spoken-word song introductions are quite powerful: "everyone wants you to forget you are gonna die, because if they convince you your not gonna die you waste your time doing what they want you to do. Spend money on what they're selling. ... one day I'm gonna die, but before then I'm gonna live, live, live, the way I want to live and I hope you do too."

Whenever I exercise I usually have caffeine as well. I view it a bit like a band aid or kick start, but I try to only use it either explicitly when walking or when intensely focusing on work.

If my back hurts from sitting at the chair too long that is a cue to get up and take a break even if it is a short one to go play with my daughter.

Sometimes I will walk two or three times throughout the day to break up the monotony.

Most my exercise is walking or jogging, but occasionally I will do a few push ups or sit ups.

In a world of gloom it is hard to look in the mirror and see a steaming pile of garbage which is not well maintained and feel good about yourself.

You know what sacrifices you have made and what the costs were, but it is easy to go down the path of resentment if outcomes are subpar and beyond your control in the short term.

If you don't feel alive you aren't. :D

It's a lifeless life, with no fixed address to give
But you're not mine to die for anymore
so I must live

Diet

I try to eat salad, Indian food, quiche, nuts, beef jerky, and all sorts of other foods where carbohydrates are sort of only incidental and are not core to the dish.

Anything that looks/smells/feels/sounds like sugar, rice, potatoes, bread, derivatives thereof, etc. I consider to be poison / systemic inflammation / weight gain and try to skip it.

I also consider drinking calories to be a disaster as the glycemic index on things like a soda are through the roof.

If you are fat and eat a lot of carbs you are repeatedly spiking your blood sugar, then it crashes, then you are hungry again. This habit & addictive cycle works on some of the same neural pathways that hardcore drugs do.

Sometimes I still do eat a bit of peanut butter or chocolate or frozen chocolate dipped in peanut butter, though I try not to use it meal replacement style very often & try not to be "full jar now empty" Aaron.

When I wake I often wait at least 4 or 5 hours before eating my first meal. In some cases I stretch that out to 6 or 8.

Communicating

I know a lot of people are in a bad state this year, so I try to offset that at least slightly by overcommunicating.

I send my mom pictures or videos of my daughter every day as she told me those help her sleep better at night and her watch even shows her blood pressure is lower and she feels much more well rested the next morning. I have bought my daughter a ton of extra clothes to wear just so my mom gets a bit more variety in the pictures and my daughter will have a ton of memories to sort through when she is older.

Our daughter has quite a bit of energy so sometimes she makes communicating with my wife hard. Sometimes we have better luck texting back and forth if something is urgent and then discuss it in more detail over email or when our daughter is taking a nap.

A lot of people around me have recently went through hardships beyond the financial uncertainties many are facing.

Our web designer's mom had a heart attack then got COVID-19 but I think she is ok now.
Our lead writer had a friend younger than I who after going to the hospital with COVID-19.
Our lead programmer's parents recently had their house broken into with some of their sentimental jewelry stolen & he is the glue guy for the whole family.
One of my buddies recently broke up with his long time girlfriend.

I am sure there are a lot more similar stories that I have not been told yet. So as a rule of thumb I sort of consider that if people have historically been good its ok to give them more leeway this year & be extra kind.

Mental Health

I generally am not a fan of taking prescription drugs to solve symptoms of real problems as in many cases those can cause additional bonus problems. I get that some people need various drugs to get by and survive, though outside of caffeine I typically try not to drink much or do much of anything else that can add more instability or create more bonus issues.

The above said, I think my baseline mood (especially if I am not in great health) tends to be a bit darker than average.

The early web was quite cool and you could do things like email Tim Berners-Lee and get a response, or someone would read your site and see you mentioned Carl Sagan and shoot you an email like this one:

I wrote the first modern book on depression in 1980. It was the first book to present depression as a biochemical disease, rather than a 'mental' illness (whatever that is). And, I was the one who introduced Carl Sagan to television as a local TV personality in L. A., Carl was a good family friend who came to watch a taping of my PBS show, he got really intense when he realized what a medium for communication TV was, and I introduced him to the GM of the station, that's how he got to TV. He was more of a scientist than an actor, I coached him on TV persona. He was a very intense person, and did not have a big ego; he was always open to new information, whether it came from experiences or ideas. He would have loved living now.

To solve both depression and weight gain problems, try an over-the-counter nutrient called 5HTP. The Walmarts here sell the least expensive and best pills. Take about nine a day for about nine days, you will notice you haven't felt the urge to eat all day and you don't have as much depression symptoms; the griffonia seed from which 5HTP is made increases serotonin in the brain.

Then a follow up after I asked about the FDA ban of L-Tryptophan:

Now something gets clearer! When tryotophan was banned because of one supposedly contaminated batch, I used every tiny bit of influence I had as a journalist, talked to every politician I could get in touch with. It was like going up against a brick wall. I wrote articles, did everything, could not understand at all why the nutrient was being banned for one bad batch in Japan and why resistance to overturning the ban was so solid. I even tried to obtain the animal version, and was told it 'wasn't the same,' yet according to a chemical analysis, it was. Now I understand....

My book is "Depression, How to Recognize It, Cure It and Grow From It, Prentice Hall hardback, Simon Schuster paperback.

She also mentioned

Depression research is such big business that I feel they don't want to find a real cure. The way the research should have gone is to study the chemical makeup of depression, then match the medication effect to different brain hormones (as well as cortisol-though it's not a biogenic amine, it's a definite precursor), and find accurate ways of testing which hormone or combination thereof is/are out of balance, so the correct medication can be prescribed right off the bat. So, if it's a seratonin imbalance, the doc gives one medication, if it's monomaine oxadase, the patient gets another, and so on. Prosac is like a huge blanket device, rather than an accurate laser beam going to the exact place it is needed.

Depression research really hasn't progressed that much in the last 20 years, imho.

I know a big part of my improved mood was from taking 5-HTP along with Vitamin B & Vitamin C just before bed. When I take those I can fall asleep a bit quicker, sleep about an hour less, wake up feeling more refreshed, and am less hungry the following morning. If I had to guess, I would say the 5-hydroxytryptophan contributed to my recent 40 pound weight loss more than anything else did.

Anyhow, I would not recommend 5-HTP for anyone who is on SSRIs, MAO inhibitors, or many other drug classes (talk to your doctor first, etc.). But I figured a lot of people feel like crap this year so I should mention it has worked well for me.

Declining Visitor Values

Aaron Wall — Tue, 07 Jul 2020 10:21:33 -0700

Late Funnel SEO Profits

Before the Panda update SEOs could easily focus almost all their energies on late funnel high-intent searches which were easy to monetize without needing to put a ton of effort into brand building or earlier funnel informational searches. This meant that SEOs could focus on phrases like [student credit cards] or [buy earbuds] or [best computer gaming headphones] or [vertical computer mouse] without needing to worry much about anything else. Make a good enough page on those topics, segment demand across options, and profit.

Due to the ability to focus content & efforts on those tiny subset high-intent commercial terms the absolute returns and CPMs from SEO investments were astronomical. Publishers could insert themselves arbitrarily just before the end of the value chain (just like Google AdWords) and extract a toll.

The Panda Shift / Eating the Info Supply Chain

Then Panda happened and sites needed to have stronger brands and/or more full funnel user experience and/or more differentiated content to be able to rank sustainably.

One over-simplified way to think of Panda and related algorithms would be: brand = rank.

Another way to look at it would be to consider the value chain of having many layers or pieces to it & Google wanting to remove as many unneeded or extra pieces from the chain as possible so that they themselves are capturing more of the value chain.

That thin eHow article about a topic without any useful info? Not needed.
The thin affiliate review which was buying Google AdSense ad impressions on that eHow article? Also not needed.
All that is really needed is the consumer intent, Google & then either Google as the retailer (pay with your credentials stored in your phone) or another trusted retailer.

In some cases there may be value in mid-market in-depth reviews, but increasingly the aggregate value offered by many of them is captured inside the search snippets along with reviews directly incorporated into the knowledge graph & aggregate review scores.

The ability to remove the extra layers is driven largely by:

the quality of the top players in the market
the number of quality publishers in a market (as long as there are 2 or more, whoever is not winning will be willing to give a lot of value to Google to try to play catch up against their stronger competitor)
the amount of usage data available in the market
the ad depth of the market

If your competitor is strong and they keep updating in-depth content pieces you can't set and forget your content and stay competitive. Across time searcher intent changes. Those who change with the markets should eventually have better engagement metrics and keep winning marketshare.

Benchmarking Your Competition

You only have to be better than whatever you are competing against to win.

If you have run out of ideas from your direct competitors in an emerging market you can typically find many more layers of optimization from looking at some of the largest and most successful players inside either the United States or China.

To give an example of how user data can be clean or a messy signal consider size 13 4E New Balance shoes. If you shop for these inside the United States a site like Amazon will have shoe size filters so you can see which shoes from that brand are available in that specific size.

In some smaller emerging markets ecommerce sites largely suck. They might allow you to filter shoes by the color blue but wanting to see the shoes available in your size is a choose your own adventure game as they do not offer those sorts of size filters, so you have to click into the shoe level, find out they do not have your size, and then try again. You do that about 100 times then eventually you get frustrated and buy off eBay or Amazon from someone who ships internationally.

In the first case it is very easy for Google to see the end user flow of users typically making their purchase at one of a few places like Amazon.com, the official New Balance store, or somewhere else like that which is likely to have the end product in stock. That second experience set is much harder to structure because the user signal is much more random with a lot more pogos back to Google.

Bigger, Better Ads

Over the past couple decades Google has grown much more aggressive at monetizing their search results. A website which sees its rank fall 1 position on mobile devices can see their mobile search traffic cut in half overnight. And desktop search results are also quite ad heavy to where sometimes a user can not see a single full organic result above the fold unless they have a huge monitor.

We tend to look at the present as being somewhat static. It is a part of human nature to think things are as they always were. But the general trend of the slow bleed squeeze is a function of math and time: "The relentless pressure to maintain Google’s growth, he said, had come at a heavy cost to the company’s users. Useful search results were pushed down the page to squeeze in more advertisements, and privacy was sacrificed for online tracking tools to keep tabs on what ads people were seeing."

Some critics have captured the broad shift in ad labeling practices, but to get a grasp of how big the shift has been look at early Google search results.

Look at how bright those ad units from 2001 are.

Since then ad labeling has grown less intuitive while ad size has increased dramatically.

Traffic Mix Shift

As publishers have been crowded out on commercial searches via larger ads & Google's vertical search properties a greater share of their overall search traffic is lower value visitors including people who have little to no commercial intent, people from emerging markets with lower disposable income and

Falling Ad Rates

Since 2010 online display ad rates have fallen about 40%.

Any individual publisher will experience those declines in a series of non-linear step function shifts. Any of the following could happen:

Google Panda or another algorithm update from a different attention merchant hits your distribution hard
a Softbank-backed competitor jumps into your market and gains a ton of press coverage using flammable money
a roll-up player buys out a series of sites in the supply chain & then tries to make the numbers back out by cramming down on ad syndication partners (sometimes you have to gain enough scale to create your own network or keep rotating through ad networks to keep them honest)
regulatory costs hit any part of the supply chain (the California parallel to GDPR just went live this month)
consumer interest shifts to other markets or solutions (the mobile phone has replaced many gadgets)
a recession causes broad-based advertiser pullbacks

Margin Eaters

In addition to lowering ad rates for peripheral websites, there are a couple other bonus margin eaters.

Junk Sunk Costs

Monopoly platforms push publishers to adopt proprietary closed code bases in order to maintain distribution: "the trade group says Google's Accelerated Mobile Pages (AMP) format was foisted on news publishers with an implied threat — their websites wouldn't show up in search results."

Decreased Supply Chain Visibility

Technical overhead leading to programmatic middlemen eating a huge piece of the pie: "From every £1 spent by an advertiser, about half goes to a publisher, roughly 16p to advertising platforms, 11p to other technology companies and 7 per cent to agencies. Adtech companies that took part in the study included Google’s dv360 and Ad Manager, Amazon Advertising and the Rubicon Project."

Selection Effect

Large attention merchants control conversion tracking systems and displace organic distribution for brands by re-routing demand through a layer of ads which allows the central network to claim responsibility for conversions which would have already happened had they not existed.

Internal employees in the marketing department and external internet marketing consultants have an incentive to play along with this game because:

it requires low effort to arbitrage your own brand
at first glance it looks wildly profitable so long as you do not realize what is going on
those who get a percent of spend can use the phantom profits from arbitraging their own brand equity to spend more money elsewhere
those who get performance based bonuses get a bonus without having to perform

Both eBay and Microsoft published studies which showed how perverse selection effect is.

The selection effect bias is the inverse of customer acquisition cost. The more well known your brand is the more incentive ad networks have to arbitrage it & the more ad networks will try to take credit for any conversion which happens.

2) Why does CAC (mostly) only go up?

When you think about, CAC is "lowest" in the beginning, because you have no customers. You can get the low-hanging fruit cost effectively.

Think ad spend. Outbound sales spend. etc. First movers are ready to buy quickly.— Elizabeth Yin (@dunkhippo33) July 6, 2020

These margin eaters are a big part of the reason so many publishers are trying to desperately shift away from ad-based business models toward subscription revenues.

Hitting Every Layer

The commodification of content hits every layer from photography....

Networking is an art and a skill... but if the gold you hold are your images, don’t trade them for the passive networking value.

Simple lesson that is difficult to accept.— Send it. (@johnondotcom) July 4, 2020

...on through to writing

When you think about it, even $1000 is really inexpensive for a single piece of content that generates 20,000+ visits from search in the 1-3 years it's alive and ranks well. That's only about 1,000 visits a month. Yet companies only want to pay writers only $200 an article — Dan Shure (@dan_shure) July 6, 2020

...and every other layer of the editorial chain.

Profiting from content creation at scale is harder than most appreciate.

The idea that a $200 piece of content is particularly cheap comes across as ill-informed as there are many headwinds and many variables. The ability to monetize content depends on a ton of factors including: how commercial is it, how hard is it to monetize, what revshare do you go, how hard is it to rank or get distribution in front of other high intent audience sets?

If an article costs $200 it would be hard to make that back if it monetizes at anything under a $10 RPM. 20,000 visits equates to 20 units of RPM.

Some articles will not spread in spite of being high quality. Other articles take significant marketing spend to help them spread. Suddenly that $200 "successful" piece is closer to $500 when one averages in nonperformers that don't spread & marketing expenses on ones that do. So then they either need the RPM to double or triple from there or the successful article needs to get at least 50,000 visits in order to break even.

A $10 RPM is quite high for many topics unless the ads are quite aggressively integrated into the content. The flip side of that is aggressive ad integration inhibits content spread & can cause algorithmic issues which prevent sustained rankings. Recall that in the most recent algorithm update Credit Karma saw some of their "money" credit card pages slide down the rankings due to aggressive monetization. And that happened to a big site which was purchased for over $7 billion. Smaller sites see greater levels of volatility. And nobody is investing $100,000s trying to break even many years down the road. If they were only trying to break even they'd buy bonds and ignore the concept of actively running a business of any sort.

Back in 2018 AdStage analyzed the Google display network and found the following: "In Q1 2018, advertisers spent, on average, $2.80 per thousand impressions (CPM), and $0.75 per click (CPC). The average click-through rate (CTR) on the GDN was 0.35%."

A web page which garnered 20,000 pageviews and had 3 ad units on each page would get a total of 210 ad clicks given a 0.35% ad CTR. At 75 cents per click that would generate $157.50.

Suddenly a "cheap" $200 article doesn't look so cheap. What's more is said business would also have other costs beyond the writing. They have to pay for project management, editorial review, hosting, ad partnerships & biz dev, etc. etc. etc.

After all those other layers of overhead a $200 article would likely need to get about 50,000 pageviews to back out. And a $1,000 piece of content might need to get a quarter million or more pageviews to back out.

Categories:

publishing & media

How to Read Google Algorithm Updates

Aaron Wall — Sun, 24 May 2020 02:24:32 -0700

Links = Rank

Old Google (pre-Panda) was to some degree largely the following: links = rank.

Once you had enough links to a site you could literally pour content into a site like water and have the domain's aggregate link authority help anything on that site rank well quickly.

As much as PageRank was hyped & important, having a diverse range of linking domains and keyword-focused anchor text were important.

Brand = Rank

After Vince then Panda a site's brand awareness (or, rather, ranking signals that might best simulate it) were folded into the ability to rank well.

Panda considered factors beyond links & when it first rolled out it would clip anything on a particular domain or subdomain. Some sites like HubPages shifted their content into subdomains by users. And some aggressive spammers would rotate their entire site onto different subdomains repeatedly each time a Panda update happened. That allowed those sites to immediately recover from the first couple Panda updates, but eventually Google closed off that loophole.

Any signal which gets relied on eventually gets abused intentionally or unintentionally. And over time it leads to a "sameness" of the result set unless other signals are used:

Google is absolute garbage for searching anything related to a product. If I'm trying to learn something invariably I am required to search another source like Reddit through Google. For example, I became introduced to the concept of weighted blankets and was intrigued. So I Google "why use a weighted blanket" and "weighted blanket benefits". Just by virtue of the word "weighted blanket" being in the search I got pages and pages of nothing but ads trying to sell them, and zero meaningful discourse on why I would use one

Getting More Granular

Over time as Google got more refined with Panda broad-based sites outside of the news vertical often fell on tough times unless they were dedicated to some specific media format or had a lot of user engagement metrics like a strong social network site. That is a big part of why the New York Times sold About.com for less than they paid for it & after IAC bought it they broke it down into a variety of sites like: Verywell (health), the Spruce (home decor), the Balance (personal finance), Lifewire (technology), Tripsavvy (travel) and ThoughtCo (education & self-improvement).

Penguin further clipped aggressive anchor text built on low quality links. When the Penguin update rolled out Google also rolled out an on-page spam classifier to further obfuscate the update. And the Penguin update was sandwiched by Panda updates on either side, making it hard for people to reverse engineer any signal out of weekly winners and losers lists from services that aggregate massive amounts of keyword rank tracking data.

So much of the link graph has been decimated that Google reversed their stance on nofollow to where in March 1st of this year they started treating it as a hint versus a directive for ranking purposes. Many mainstream media websites were overusing nofollow or not citing sources at all, so this additional layer of obfuscation on Google's part will allow them to find more signal in that noise.

March 4, 2020 Algo Update

On May 4th Google rolled out another major core update.

Later today, we are releasing a broad core algorithm update, as we do several times per year. It is called the May 2020 Core Update. Our guidance about such updates remains as we’ve covered before. Please see this blog post for more about that:https://t.co/e5ZQUAlt0G— Google SearchLiaison (@searchliaison) May 4, 2020

I saw some sites which had their rankings suppressed for years see a big jump. But many things changed at once.

Wedge Issues

On some political search queries which were primarily classified as being news related Google is trying to limit political blowback by showing official sites and data scraped from official sites instead of putting news front & center.

"Google’s pretty much made it explicit that they’re not going to propagate news sites when it comes to election related queries and you scroll and you get a giant election widget in your phone and it shows you all the different data on the primary results and then you go down, you find Wikipedia, you find other like historical references, and before you even get to a single news article, it’s pretty crazy how Google’s changed the way that the SERP is intended."

That change reflects the permanent change to the news media ecosystem brought on by the web.

The Internet commoditized the distribution of facts. The "news" media responded by pivoting wholesale into opinions and entertainment.— Naval (@naval) May 26, 2016

YMYL

A blog post by Lily Ray from Path Interactive used Sistrix data to show many of the sites which saw high volatility were in the healthcare vertical & other your money, your life (YMYL) categories.

Aggressive Monetization

One of the more interesting pieces of feedback on the update was from Rank Ranger, where they looked at particular pages that jumped or fell hard on the update. They noticed sites that put ads or ad-like content front and center may have seen sharp falls on some of those big money pages which were aggressively monetized:

Seeing this all but cements the notion (in my mind at least) that Google did not want content unrelated to the main purpose of the page to appear above the fold to the exclusion of the page's main content! Now for the second wrinkle in my theory.... A lot of the pages being swapped out for new ones did not use the above-indicated format where a series of "navigation boxes" dominated the page above the fold.

The above shift had a big impact on some sites which are worth serious money. Intuit paid over $7 billion to acquire Credit Karma, but their credit card affiliate pages recently slid hard.

Credit Karma lost 40% traffic from May core update. That’s insane, they do major TV ads and likely pay millions in SEO expenses. Think about that folks. Your site isn’t safe. Google changes what they want radically with every update, while telling us nothing!— SEOwner (@tehseowner) May 14, 2020

The above sort of shift reflects Google getting more granular with their algorithms. Early Panda was all or nothing. Then it started to have different levels of impact throughout different portions of a site.

Brand was sort of a band aid or a rising tide that lifted all (branded) boats. Now we are seeing Google get more granular with their algorithms where a strong brand might not be enough if they view the monetization as being excessive. That same focus on page layout can have a more adverse impact on small niche websites.

One of my old legacy clients had a site which was primarily monetized by the Amazon affiliate program. About a month ago Amazon chopped affiliate commissions in half & then the aggressive ad placement caused search traffic to the site to get chopped in half when rankings slid on this update.

Their site has been trending down over the past couple years largely due to neglect as it was always a small side project. They recently improved some of the content about a month or so ago and that ended up leading to a bit of a boost, but then this update came. As long as that ad placement doesn't change the declines are likely to continue.

They just recently removed that ad unit, but that meant another drop in income as until there is another big algo update they're likely to stay at around half search traffic. So now they have a half of a half of a half. Good thing the site did not have any full time employees or they'd be among the millions of newly unemployed. That experience though really reflects how websites can be almost like debt levered companies in terms of going under virtually overnight. Who can have revenue slide around 88% and then take increase investment in the property using the remaining 12% while they wait for the site to be rescored for a quarter year or more?

"If you have been negatively impacted by a core update, you (mostly) cannot see recovery from that until another core update. In addition, you will only see recovery if you significantly improve the site over the long-term. If you haven’t done enough to improve the site overall, you might have to wait several updates to see an increase as you keep improving the site. And since core updates are typically separated by 3-4 months, that means you might need to wait a while."

Almost nobody can afford to do that unless the site is just a side project.

Google could choose to run major updates more frequently, allowing sites to recover more quickly, but they gain economic benefit in defunding SEO investments & adding opportunity cost to aggressive SEO strategies by ensuring ranking declines on major updates last a season or more.

Choosing a Strategy vs Letting Things Come at You

They probably should have lowered their ad density when they did those other upgrades. If they had they likely would have seen rankings at worst flat or likely up as some other competing sites fell. Instead they are rolling with a half of a half of a half on the revenue front. Glenn Gabe preaches the importance of fixing all the problems you can find rather than just fixing one or two things and hoping it is enough. If you have a site which is on the edge you sort of have to consider the trade offs between various approaches to monetization.

monetize it lightly and hope the site does well for many years
monetize it slightly aggressively while using the extra income to further improve the site elsewhere and ensure you have enough to get by any lean months
aggressively monetize the shortly after a major ranking update if it was previously lightly monetized & then hope to sell it off a month or two later before the next major algorithm update clips it again

Outcomes will depend partly on timing and luck, but consciously choosing a strategy is likely to yield better returns than doing a bit of mix-n-match while having your head buried in the sand.

Reading the Algo Updates

You can spend 50 or 100 hours reading blog posts about the update and learn precisely nothing in the process if you do not know which authors are bullshitting and which authors are writing about the correct signals.

But how do you know who knows what they are talking about?

It is more than a bit tricky as the people who know the most often do not have any economic advantage in writing specifics about the update. If you primarily monetize your own websites, then the ignorance of the broader market is a big part of your competitive advantage.

Making things even trickier, the less you know the more likely Google would be to trust you with sending official messaging through you. If you syndicate their messaging without questioning it, you get a treat - more exclusives. If you question their messaging in a way that undermines their goals, you'd quickly become persona non grata - something cNet learned many years ago when they published Eric Schmidt's address.

It would be unlikely you'd see the following sort of Tweet from say Blue Hat SEO or Fantomaster or such.

I asked Gary about E-A-T. He said it's largely based on links and mentions on authoritative sites. i.e. if the Washington post mentions you, that's good.

He recommended reading the sections in the QRG on E-A-T as it outlines things well.@methode #Pubcon— Marie Haynes (@Marie_Haynes) February 21, 2018

To be able to read the algorithms well you have to have some market sectors and keyword groups you know well. Passively collecting an archive of historical data makes the big changes stand out quickly.

Everyone who depends on SEO to make a living should subscribe to an online rank tracking service or run something like Serposcope locally to track at least a dozen or two dozen keywords. If you track rankings locally it makes sense to use a set of web proxies and run the queries slowly through each so you don't get blocked.

You should track at least a diverse range to get a true sense of the algorithmic changes.

a couple different industries
a couple different geographic markets (or at least some local-intent vs national-intent terms within a country)
some head, midtail and longtail keywords
sites of different size, age & brand awareness within a particular market

Some tools make it easy to quickly add or remove graphing of anything which moved big and is in the top 50 or 100 results, which can help you quickly find outliers. And some tools also make it easy to compare their rankings over time. As updates develop you'll often see multiple sites making big moves at the same time & if you know a lot about the keyword, the market & the sites you can get a good idea of what might have been likely to change to cause those shifts.

Once you see someone mention outliers most people miss that align with what you see in a data set, your level of confidence increases and you can spend more time trying to unravel what signals changed.

I've read influential industry writers mention that links were heavily discounted on this update. I have also read Tweets like this one which could potentially indicate the opposite.

Check out https://t.co/1GhD2U01ch . Up even more than Pinterest and ranking for some real freaky shit.— Paul Macnamara (@TheRealpmac) May 12, 2020

If I had little to no data, I wouldn't be able to get any signal out of that range of opinions. I'd sort of be stuck at "who knows."

By having my own data I track I can quickly figure out which message is more inline with what I saw in my subset of data & form a more solid hypothesis.

No Single Smoking Gun

As Glenn Gabe is fond of saying, sites that tank usually have multiple major issues.

Google rolls out major updates infrequently enough that they can sandwich a couple different aspects into major updates at the same time in order to make it harder to reverse engineer updates. So it does help to read widely with an open mind and imagine what signal shifts could cause the sorts of ranking shifts you are seeing.

Sometimes site level data is more than enough to figure out what changed, but as the above Credit Karma example showed sometimes you need to get far more granular and look at page-level data to form a solid hypothesis.

As the World Changes, the Web Also Changes

About 15 years ago online dating was seen as a weird niche for recluses who perhaps typically repulsed real people in person. Now there are all sorts of niche specialty dating sites including a variety of DTF type apps. What was once weird & absurd had over time become normal.

The COVID-19 scare is going to cause lasting shifts in consumer behavior that accelerate the movement of commerce online. A decade of change will happen in a year or two across many markets.

Telemedicine will grow quickly. Facebook is adding commerce featured directly onto their platform through partnering with Shopify. Spotify is spending big money to buy exclusives rights to distribute widely followed podcasters like Joe Rogan. Uber recently offered to acquire GrubHub. Google and Apple will continue adding financing features to their mobile devices. Movie theaters have lost much of their appeal.

Tons of offline "value" businesses ended up having no value after months of revenue disappearing while large outstanding debts accumulated interest. There is a belief that some of those brands will have strong latent brand value that carries over online, but if they were weak even when the offline stores acting like interactive billboards subsidized consumer awareness of their brands then as those stores close the consumer awareness & loyalty from in-person interactions will also dry up. A shell of a company rebuilt around the Toys R' Us brand is unlikely to beat out Amazon's parallel offering or a company which still runs stores offline.

Big box retailers like Target & Walmart are growing their online sales at hundreds of percent year over year.

There will be waves of bankruptcies, shifts in commercial real estate prices, more people working remotely (shifting residential real estate demand from the urban core back out into suburbs).

More and more activities will become normal online activities.

The University of California has about a half-million students & in the fall semester they are going to try to have most of those classes happen online. How much usage data does Google gain as thousands of institutions put more and more of their infrastructure and service online?

Colleges have to convince students for the next year that a remote education is worth every bit as much as an in-person one, and then pivot back before students actually start believing it.

It’s like only being able to sell your competitor’s product for a year.— Naval (@naval) May 6, 2020

A lot of B & C level schools are going to go under as the like-vs-like comparison gets easier. Back when I ran a membership site here a college paid us to have students gain access to our membership area of the site. As online education gets normalized many unofficial trade-related sites will look more economically attractive on a relative basis.

Categories:

google

Easy for You

Aaron Wall — Wed, 13 May 2020 15:21:01 -0700

To Teach, One Must Learn

One of the benefits of writing is it forces you to structure your thoughts.

If you are doing something to pass a test rote memorization can work, but if you are trying to teach someone else and care it forces you to know with certainty what you are teaching.

When I was in nuclear power school one guy was about to flunk out and I did not want to let him so I taught him stuff for days. He passed that test and as a side effect I got my highest score I ever got on one of those tests. He eventually did flunk out, but he knew other people were rooting for him and tried to help him.

Market Your Work or Become Redundant

Going forward as more work becomes remote it is going to be easier to hire and fire people. The people who are great at sharing their work and leaving a public record of it will likely be swimming in great opportunities, whereas some equally talented people who haven't built up a bit of personal brand equity will repeatedly get fired in spite of being amazingly talented, simply because there was a turn in the economy and management is far removed from the talent. As bad as petty office politics can be, it will likely become more arbitrary when everyone is taking credit for the work of others & people are not sitting side by side to see who actually did the work.

Uber recently announced they were laying off thousands of employees while looking to move a lot of their core infrastructure work overseas where labor is cheaper. Lots of people will be made redundant as unicorn workers in a recession suddenly enjoy the job stability and all the perks of the gig working economy.

Design

We have a great graphic designer who is deeply passionate about his work. He can hand draw amazing art or comics and is also great at understanding illustration software, web design, web usability, etc. I have no idea why he was fired from his prior employer but am thankful he was as he has been a joy to work with.

Before COVID-19 killed office work I sat right next to our lead graphic designer and when I would watch him use Adobe Illustrator I was both in awe of him and annoyed at how easy he would make things look. He is so good at it that and endless array of features are second nature to him. When I would ask him how to do something I just saw him do frequently it would be harder for him to explain how he does it than doing it.

Programming

Our graphics designer is also a quite solid HTML designer, though strictly front end design. One day when I took an early lunch with my wife I asked him to create a Wordpress theme off his HTML design and when I got back he was like ... ummm. :)

We are all wizards at some things and horrible at others. When I use Adobe Illustrator for even the most basic tasks I feel like a guy going to a breakdancing party with no cardboard and 2 left shoes.

There are a number of things that are great about programming

it is largely logic-based
people drawn toward it tend to be smart
people who can organize code also tend to use language directly (making finding solutions via search rather easy)

Though over time programming languages change features & some changes are not backward compatible. And as some free & open source projects accumulate dependencies they end up promoting the use of managers. Some of these may not be easy to install & configure on a remote shared server (with user permission issues) from a Windows computer. So then you install another package on your local computer and then have to research how it came with a deprecated php track_errors setting. And on and on.

One software program I installed on about a half-dozen sites many moons ago launched a new version recently & the typical quick 5 minute install turned into a half day of nothing. The experience felt a bit like a "choose your own adventure" book, where almost every choice you make leads to: start again at the beginning.

At that point a lot of the advice one keeps running into sort of presumes one has the exact same computer set up they do, so search again, solve that problem, turn on error messaging, and find the next problem to ... once again start at the beginning.

That sort of experience is more than a bit humbling & very easy to run into when one goes outside their own sphere of expertise.

Losing the Beginner's Mindset

If you do anything for an extended period of time it is easy to take many things for granted as you lose the beginner's mindset.

One of the reasons it is important to go outside your field of expertise is to remind yourself of what that experience feels like.

Anyone who has been in SEO for a decade likely does the same thing when communicating about search by presuming the same level of domain expertise and talking past people. Some aspects of programming are hard because they are complex. But when you are doing simple and small jobs then if things absolutely do not work you often get the answer right away. Whereas with SEO you can be unsure of the results of a large capital and labor investment until the next time a core algorithm update happens a quarter year from now. That uncertainty acts as the barrier to entry & blocker of institutional investments which allow for sustained above average profit margins for those who make the cut, but it also means a long lag time and requiring a high level of certainty to make a big investment.

The hard part about losing the beginners mindset with SEO is sometimes the algorithms do change dramatically and you have to absolutely reinvent yourself while throwing out what you know (use keyword rich anchor text aggressively, build tons of links, exact match domains beat out brands, repeat keyword in bold on page, etc.) and start afresh as the algorithms reshuffle the playing field.

The Web Keeps Changing

While the core algorithms are shifting so too is how people use the web. Any user behaviors are shifting as search results add more features and people search on mobile devices or search using their voice. Now that user engagement is a big part of ranking, anything which impacts brand perception or user experience also impacts SEO. Social distancing will have major impacts on how people engage with search. We have already seen a rapid rise of e-commerce at the expense of offline sales & some colleges are planning on holding next year entirely online. The University of California will have roughly a half-million students attending school online next year unless students opt for something cheaper.

Colleges have to convince students for the next year that a remote education is worth every bit as much as an in-person one, and then pivot back before students actually start believing it.

It’s like only being able to sell your competitor’s product for a year.— Naval (@naval) May 6, 2020

What Resolution?

I am horrible with Adobe Illustrator. But one of the things I have learned with that and Photoshop is that if you edit in a rather high resolution you can have many of your errors disappear to the naked eye when it is viewed at a normal resolution. The same analogy holds true for web design but in the opposite direction ... if your usability is solid on a mobile device & the design looks good on a mobile device then it will probably be decent on desktop as well.

Some people also make a resolution mistake with SEO.

If nobody knows about a site or brand or company having perfect valid HTML, supporting progressive web apps, supporting AMP, using microformats, etc. ... does not matter.
On the flip side, if a site is well known it can get away with doing many things sub-optimally & can perhaps improve a lot by emulating sites which are growing over time in spite of having weaker brand strength.

Free, so Good Enough?

Many open source software programs do not do usability testing or track the efforts of a somewhat average user or new user in their ability to download and install software because they figure it is free so oh well people should figure it out. That thinking is a mistake though, because each successive increase in barrier to entry limits your potential market size & eventually some old users leave for one reason or another.

Any free software project which accumulates attention and influence can be monetized in other ways (through consulting, parallel SaaS offerings, affiliate ad integration, partnering with Hot Nacho to feature some great content in a hidden div using poetic code, etc.). But if they lack reach, see slowing growth, and then increase the barrier to entry they are likely to die.

When you ask someone to pay for something you'll know if they like it and where they think it can be improved. Relying on the free price point hides many problems and allows them to accumulate.

The ability to make things easy for absolute beginners is a big part of why Wordpress is worth many multiples of what Acquia sold for. And Wordpress has their VIP hosting service, Akismet, and a bunch of other revenue streams while Acquia is now owned by a private equity company.

The ability to be 0.0000001% as successful as Wordpress has been without losing the beginner mindset is hard.

Categories:

marketing

New Age Cloaking

Aaron Wall — Tue, 12 May 2020 01:34:40 -0700

Historically cloaking was considered bad because a consumer would click expecting a particular piece of content or user experience while being delivered an experience which differed dramatically.

As publishers have become more aggressive with paywalls they've put their brands & user trust in the back seat in an attempt to increase revenue per visit.

Below are 2 screenshots from one of the more extreme versions I have seen recently.

The first is a subscribe-now modal which shows by default when you visit the newspaper website.

The second is the page as it appears after you close the modal.

Basically all page content is cloaked other than ads and navigation.

The content is hidden - cloaked.

That sort of behavior would not only have a horrible impact on time on site metrics, but it would teach users not to click on their sites in the future, if users even have any recall of the publisher brand.

The sort of disdain that user experience earns will cause the publishers to lose relevancy even faster.

On the above screenshot I blurred out the logo of the brand on the initial popover, but when you look at the end article after that modal pop over you get a cloaked article with all the ads showing and the brand of the site is utterly invisible. A site which hides its brand except for when it is asking for money is unlikely to get many conversions.

Many news sites now look as awful as the ugly user created MySpace pages did back in the day. And outside of the MySpace pages that delivered malware the user experience is arguably worse.

Each news site which adopts this approach effectively increases user hate toward all websites adopting the approach.

It builds up. Then users eventually say screw this. And they are gone - forever.

Audiences will thus continue to migrate across from news sites to anywhere else that hosts their content like Google AMP, Facebook Instant Articles, Apple News, Twitter, Opera or Edge or Chrome mobile browser new article recommendations, MSN News, Yahoo News, etc.

Any lifetime customer value models built on assumptions around any early success with the above approach should consider churn as well as the brand impact the following experience will have on most users before going that aggressive.

One small positive note for news publishers is more countries are looking to have attention merchants pay for their content, though I suspect as the above sort of double modal paywall stuff gets normalized other revenue streams won't make the practice go away, particularly as many local papers have been acquired by PE chop shops extracting all blood out of the operations through interest payments to themselves.

Categories:

publishing & media

Managing Algorithmic Volatility

Aaron Wall — Sun, 10 May 2020 20:30:47 -0700

Upon the recently announced Google update I've seen some people Tweet things like

if you are afraid of algorithm updates, you must be a crappy SEO
if you are technically perfect in your SEO, updates will only help you

I read those sorts of lines and cringe.

Here's why...

Fragility

Different businesses, business models, and business structures have varying degrees of fragility.

If your business is almost entirely based on serving clients then no matter what you do there is going to be a diverse range of outcomes for clients on any major update.

Let's say 40% of your clients are utterly unaffected by an update & of those who saw any noticeable impact there was a 2:1 ratio in your favor, with twice as many clients improving as falling.

Is that a good update? Does that work well for you?

If you do nothing other than client services as your entire business model, then that update will likely suck for you even though the net client impact was positive.

Why?

Many businesses are hurting after the Covid-19 crisis. Entire categories have been gutted & many people are looking for any reason possible to pull back on budget. Some of the clients who won big on the update might end up cutting their SEO budget figuring they had already won big and that problem was already sorted.

Some of the clients that fell hard are also likely to either cut their budget or call endlessly asking for updates and stressing the hell out of your team.

Capacity Utilization Impacts Profit Margins

Your capacity utilization depends on how high you can keep your steady state load relative to what your load looks like at peaks. When there are big updates management or founders can decide to work double shifts and do other things to temporarily deal with increased loads at the peak, but that can still be stressful as hell & eat away at your mental and physical health as sleep and exercise are curtailed while diet gets worse. The stress can be immense if clients want results almost immediately & the next big algorithm update which reflects your current work may not happen for another quarter year.

How many clients want to be told that their investments went sour but the problem was they needed to double their investment while cashflow is tight and wait a season or two while holding on to hope?

Category-based Fragility

Businesses which appear to be diversified often are not.

Everything in hospitality was clipped by Covid-19.
40% of small businesses across the United States have stopped making rent payments.
When restaurants massively close that's going to hit Yelp's business hard.
Auto sales are off sharply.

Likewise there can be other commonalities in sites which get hit during an update. Not only could it include business category, but it could also be business size, promotional strategies, etc.

Sustained profits either come from brand strength, creative differentiation, or systemization. Many prospective clients do not have the budget to build a strong brand nor the willingness to create something that is truly differentiated. That leaves systemization. Systemization can leave footprints which act as statistical outliers that can be easily neutralized.

Sharp changes can happen at any point in time.

For years Google was funding absolute garbage like Mahalo autogenerated spam and eHow with each month being a new record. It is very hard to say "we are doing it wrong" or "we need to change everything" when it works month after month after month.

Then an update happens and poof.

Was eHow decent back in the first Internet bubble? Sure. But it lost money.
Was it decent after it got bought out for a song and had the paywall dropped in favor of using the new Google AdSense program? Sure.
Was it decent the day Demand Media acquired it? Sure.
Was it decent on the day of the Demand Media IPO? Almost certainly not. But there was a lag between that day and getting penalized.

Panda Trivia

The first Panda update missed eHow because journalists were so outraged by the narrative associated with the pump-n-dump IPO. They feared their jobs going away and being displaced by that low level garbage, particularly as the market cap of Demand Media eclipsed the New York Times.

Journalist coverage of the pump-n-dump IPO added credence to it from an algorithmic perspective. By constantly writing hate about eHow they made eHow look like a popular brand, generating algorithmic signals that carried the site until Google created an extension which allowed journalists and other webmasters to vote against the site they had been voting for through all their outrage coverage.

Algorithms & the Very Visible Hand

And all algorithmic channels like organic search, the Facebook news feed, or Amazon's product pages go through large shifts across time. If they don't, they get gamed, repetitive, and lose relevance as consumer tastes change and upstarts like Tiktok emerge.

Consolidation by the Attention Merchants

Frequent product updates, cloning of upstarts, or outright acquisitions are required to maintain control of distribution:

"The startups of the Rebellion benefited tremendously from 2009 to 2012. But from 2013 on, the spoils of smartphone growth went to an entirely different group: the Empire. ... A network effect to engage your users, AND preferred distribution channels to grow, AND the best resources to build products? Oh my! It’s no wonder why the Empire has captured so much smartphone value and created a dark time for the Rebellion. ... Now startups are fighting for only 5% of the top spots as the Top Free Apps list is dominated by incumbents. Facebook (4 apps), Google (6 apps), and Amazon (4 apps) EACH have as many apps in the Top 100 list as all the new startups combined."

Apple & Amazon

Emojis are popular, so those features got copied, those apps got blocked & then apps using the official emojis also got blocked from distribution. The same thing happens with products on Amazon.com in terms of getting undercut by a house brand which was funded by using the vendor's sales data. Re-buy your brand or else.

Facebook

Before the Facebook IPO some thought buying Zynga shares was a backdoor way to invest into Facebook because gaming was such a large part of the ecosystem. That turned out to be a dumb thesis and horrible trade. At times other things trended including quizzes, videos, live videos, news, self hosted Instant Articles, etc.

Over time the general trend was edge rank of professional publishers fell as a greater share of inventory went to content from friends & advertisers. The metrics associated with the ads often overstated their contribution to sales due to bogus math and selection bias.

Internet-first publishers like CollegeHumor struggled to keep up with the changes & influencers waiting for a Facebook deal had to monetize using third parties:

“I did 1.8 billion views last year,” [Ryan Hamilton] said. “I made no money from Facebook. Not even a dollar.” ... "While waiting for Facebook to invite them into a revenue-sharing program, some influencers struck deals with viral publishers such as Diply and LittleThings, which paid the creators to share links on their pages. Those publishers paid top influencers around $500 per link, often with multiple links being posted per day, according to a person who reached such deals."

YouTube

YouTube had a Panda-like update back in 2012 to favor watch time over raw view counts. They also adjust the ranking algorithms on breaking news topics to favor large & trusted channels over conspiracy theorist content, alternative health advice, hate speech & ridiculous memes like the Tide pod challenge.

All unproven channels need to start somewhat open to gain usage, feedback & marketshare. Once they become real businesses they clamp down. Some of the clamp down can be editorial, forced by regulators, or simply anticompetitive monpolistic abuse.

Kid videos were a huge area on YouTube (perhaps still are) but that area got cleaned up after autogenerated junk videos were covered & the FTC clipped YouTube for delivering targeted ads on channels which primarily catered to children.

Dominant channels can enforce tying & bundling to wipe out competitors:

"Google’s response to the threat from AppNexus was that of a classic monopolist. They announced that YouTube would no longer allow third-party advertising technology. This was a devastating move for AppNexus and other independent ad technology companies. YouTube was (and is) the largest ad-supported video publisher, with more than 50% market share in most major markets. ... Over the next few months, Google’s ad technology team went to each of our clients and told them that, regardless of how much they liked working with AppNexus, they would have to also use Google’s ad technology products to continue buying YouTube. This is the definition of bundling, and we had no recourse. Even WPP, our largest customer and largest investors, had no choice but to start using Google’s technology. AppNexus growth slowed, and we were forced to lay off 100 employees in 2016."

Everyone Else

Every moderately large platform like eBay, Etsy, Zillow, TripAdvisor or the above sorts of companies runs into these sorts of issues with changing distribution & how they charge for distribution.

Building Anti-fragility Into Your Business Model

Growing as fast as you can until the economy craters or an algorithm clips you almost guarantees a hard fall along with an inability to deal with it.

Markets ebb and flow. And that would be true even if the above algorithmic platforms did not make large, sudden shifts.

Build Optionality Into Your Business Model

If your business primarily relies on publishing your own websites or you have a mix of a few clients and your own sites then you have a bit more optionality to your approach in dealing with updates.

Even if you only have one site and your business goes to crap maybe you at least temporarily take on a few more consulting clients or do other gig work to make ends meet.

Focus on What is Working

If you have a number of websites you can pour more resources into whatever sites reacted positively to the update while (at least temporarily) ignoring any site that was burned to a crisp.

Ignore the Dead Projects

The holding cost of many websites is close to zero unless they use proprietary and complex content management systems. Waiting out a penalty until you run out of obvious improvements on your winning sites is not a bad strategy. Plus, if you think the burned site is going to be perpetually burned to a crisp (alternative health anyone?) then you could sell links off it or generate other alternative revenue streams not directly reliant on search rankings.

Build a Cushion

If you have cash savings maybe you guy out and buy some websites or domain names from other people who are scared of the volatility or got clipped for issues you think you could easily fix.

When the tide goes out debt leverage limits your optionality. Savings gives you optionality. Having slack in your schedule also gives you optionality.

The person with a lot of experience & savings would love to see highly volatile search markets because those will wash out some of the competition, curtail investments from existing players, and make other potential competitors more hesitant to enter the market.

Categories:

internet

New Version of SEO Toolbar

Aaron Wall — Mon, 04 May 2020 06:09:22 -0700

Our programmer recently updated our SEO toolbar to work with the most recent version of Firefox.

You can install it from here. After you install it the toolbar should automatically update on a forward basis.

It is easy to toggle on or off simply by clicking on the green or gray O. If the O is gray it is off & if it is green it is on.

The toolbar shows site & page level link data from data sources like SEMRush, Ahrefs & Majestic along with estimated Google search traffic from SEMrush and some social media metrics.

At the right edge of the toolbar there is a [Tools] menu which allows you to pull in the age of a site from the Internet Archive Wayback Machine, the IP address hosting a site & then cross links into search engine cached copies of pages and offers access to our SEO Xray on-page analyzer.

SEO today is much more complex than it was back when we first launched this toolbar as back them almost everything was just links, links, links. All metrics in isolation are somewhat useless, but being able to see estimated search traffic stats right near link data & being able to click into your favorite data sources to dig deeper into the data can help save a lot of time.

For now the toolbar is still only available on Firefox, though we could theoretically have it work on Chrome *if* at some point we trusted Google.

Categories:

seo tools

China Still Censoring Google, Now Globally

Aaron Wall — Tue, 28 Apr 2020 12:28:49 -0700

Google Gets Out of China

In March of 2010 Google announced they would no longer censor their search results for China:

earlier today we stopped censoring our search services—Google Search, Google News, and Google Images—on Google.cn. Users visiting Google.cn are now being redirected to Google.com.hk, where we are offering uncensored search in simplified Chinese, specifically designed for users in mainland China and delivered via our servers in Hong Kong.

While the move was pitched as altruistic, it came only after the state put their thumb on the scales to promote domestic competitor Baidu in part by periodically blocking Google search from working.

The Value of Leaving China

By leaving China on their own accord, Google controlled the narrative for investors. They didn't "lose" a market, they chose to not operate in a market.

If you are destined to lose due to political interference, you may as well look principled in the process. The idea of staying the course (being highly compromised while also losing) would have lowered Google's leverage (over publishers and governments) as well as their brand value elsewhere.

Think of how long Google has kept the EU at bay in terms of their anti-competitive practices in search.

Countries like France and Australia are just now beginning to require payment to publishers from Google.

In spite of being in fifth place with about 2% search marketshare in China, one could easily argue that today Google is *still* being censored by China, except now it is global.

Official != Legitimate

Whenever there is a crisis Google has the ability to adjust their news algorithms (and rankings on other sources like YouTube) to prefer authoritative sources. If China lies but gives a direct quote that is an official response which can be reported in the media. Speculating, on the other hand, is not news, and thus is not likely to be done at scale on official sources.

The WHO parroted the official line of the Chinese Communist Party for months before sending in a team to begin investigating the virus which was quietly spreading globally in the background. This is evil (or, more charitably, ill-informed) their advice was:

Tedros said there was no need for measures that “unnecessarily interfere with international travel and trade,” and he specifically said that stopping flights and restricting Chinese travel abroad was “counter-productive” to fighting the global spread of the virus.

Evidence is Backward Looking

Promoting "consistent, evidence-based" risk control is utterly stupid because the evidence that you are dead only appears after you die.

It is not a game of 50/50 chance.

One outcome is death. And at the other end of the spectrum you spent $15 needlessly on a facemask.

How lowly must you view the value of a human life to determine a $15 spend on risk mitigation is reckless behavior?

Don't exceed the global standards based on China's misinformation. OR ELSE!!!

WHO can hold countries to account when they needlessly exceed these global standards. This is critical to ensuring the international response is evidence-based, measured & balanced to protect human health in ways that are neither over-reactive nor under-reactive.- Dr Houssin pic.twitter.com/HaRMNXpmOb— World Health Organization (WHO) (@WHO) January 30, 2020

Evidence is backward looking even if the sources are not lying scum. When lying is vital to maintaining political power many people die while waiting on the true.

Can anyone who followed official anti-warnings get a refund on their death?

Better luck next life?

Evidence

Later, as evidence emerged, we find that wearing a facemask is a great idea, in spite of early media reports they would not help you.
Later, as evidence emerged, we find the WHO sponsored doctors who published studies which showed official Chinese numbers were bogus.
Later, as evidence emerged, we learn that the CCP are lying, jackbooted thugs. They had coronavirus research destroyed, arrested doctors who mentioned the issue, and held secret internal meetings discussing human to human transmission even as the WHO stated the risk was low & there was no clear evidence of human-to-human transmission, so there should be no restrictions on international travel.
Later, as evidence emerged, we find that closing borders is a great idea - even China does it. Of course early media reports were to not be xenophobic or racist and accept this global problem: "Ultimately some pandemic responses will require opening borders, not closing them. At some point the expectation that any area will escape effects of COVID-19 must be abandoned: The disease must be seen as everyone’s problem."
Later, as evidence emerged, we learn that Taiwan warned the WHO of human to human transmission last December.
Later, as evidence emerged, we learned that WHO representatives Bruce Aylward hung up on a journalist who brought up the topic of Taiwan. This problem got "solved" by the news organization being reprimanded.

‼️WOW‼️ Bruce Aylward/@WHO did an interview with HK's @rthk_news & when asked about #Taiwan he pretended not to hear the question. The journalist asks again & he hangs up! She calls back & he said "Well, we've already talked about China."ENJOY+SHARE THE MADNESS! #CoronaVirus pic.twitter.com/jgpHRVHjNX— Hong Kong World City (@HKWORLDCITY) March 28, 2020

While China's CCP was lying to the world, the WHO shared appreciation for their commitment to sharing info.

Not Just China

Health officials the world over were guilty of the same sort of "evidence-based" stupidity.

Here is a video from February of NYC health commissioner Dr. Oxiris Barbot advising people to go out and take the subway and live their lives, noting that city preparedness is high, their personal risk is low, and casual contact was not a large risk.

How much of a risk is the new coronavirus to New York City?Health Commissioner Dr. Oxiris Barbot explains to @InsideCityHall how likely it is to transmit the virus. #NY1Politics pic.twitter.com/mUbU8F0p3N— Spectrum News NY1 (@NY1) February 7, 2020

You can see the stupidity in the circular logic here: "we also know that if it were likely to be transmitted casually we would be seeing a lot more cases."

Yes we would!
Or soon would be.
And did.

Time shift that statement a couple months and lawmakers are asking her to be fired.

May you enjoy a happy Lunar New Year:

“We are very clear: We wish New Yorkers a Happy Lunar New Year and we encourage people to spend time with their families and go about their celebration,” Dr. Barbot said.

Later, as evidence emerged, we learn from serological studies that around 24.7% of people in New York City & 14.9% of New York state had antibodies for the coronavirus that causes COVID-19.

If you are a poor minority you are more likely to die as you have less of a cushion to do things like taking time off work and AVOID TAKING THE SUBWAY.

Thank you Dr. Oxiris Barbot!

Even the New York Times warned against quarantines, virtually guaranteeing the city would get one.

Protecting Yourself from Dr. Oxiris Barbot & the CCP

How many billions of dollars do people spend buying lotto tickets?

A high-quality facemask was a $15 lotto ticket that might save you from death. But buying one was ill-informed & xenophic & antisocial and and and.

Back in January I saw a video on Twitter of a guy walking down the street in Wuhan and then just fall over and die. Upon seeing that, I quickly ordered facemasks for my wife, our babysitter, my wife's parents, my mom, and my siblings.

My mom thought I was crazy for spending hundreds buying so many masks, but it was a fairly simple calculation. Whatever China was saying was hot garbage as they were literally welding apartment complexes shut.

Ongoing Disinformation Campaign

They accosted doctors who warned of the pending pandemic, locked down millions of people, and held internal briefs about human to human transmission was happening while lying externally about it. China then pushed some garbage about how the US Army created the coronavirus which caused COVID-19, then they both claimed it was racist to state the disease came from China while also claiming it originated in Italy.

That's the CCP - literally zero shame.

You can be against the jackbooted CCP while not hating Chinese people. I would rather be wrongly called a racist and not die of coronavirus than virtue signal my way to death via Italy's "Hug a Chinese" day.

As a general rule of thumb, life is more important than the feelz.

My wife took a DNA test and a big part of her ethnic background is Chinese. When she and I are in the Philippines many people think she is a foreigner. When I was walking with my wife in Hong Kong years ago a local street vender started talking to her in Chinese thinking she was a local. And there's nobody in the world I love more than her, but that does not mean she or I are planning a trip to Wuhan anytime soon or wanted to end up as statistics as a side effect of virtue signaling.

To this day China is using their ability to purchase foreign debts & infrastructure across weaker European countries to push the EU to understate the culpability of the CCP:

"Bowing to heavy pressure from Beijing, European Union officials softened their criticism of China this week in a report documenting how governments push disinformation about the coronavirus pandemic, according to documents, emails and interviews. Worried about the repercussions, European officials first delayed and then rewrote the document in ways that diluted the focus on China, a vital trading partner ... China moved quickly to block the document’s release, and the European Union pulled back. The report had been on the verge of publication, until senior officials ordered revisions to soften the language."

Maintaining The Illusion of Stability

The doom scenario for China would be one where the disease spread widely across their society while not directly impacting other economies. Currencies float and trade can eventually be re-routed if supply chains are unreliable. If a place where repeated coronavirus outbreaks happen has massive hidden debts in their shadow economy the propped up currency peg would likely fall as those debts go bad and their economy crashes. Hot money has been rushing out of China for years: their companies buying foreign companies, individuals buying foreign real estate, short domain names, Bitcoin, life insurance policies, etc.

China already faced sharp food price inflation last year as African Swine Flu killed a lot of their herd. When people can't afford to eat they are more likely to push for political change. Hyperinflation is the reciprocal of political stability. Maintaining a stable food supply is a core requirement of staying in power.

Masks might make no difference, but if I spend a fraction of a percent of my income protecting my immediate and extended family even slightly then that is a good investment.

What is the price of a single needless death?

That is the calculation one should use when adopting simple & cheap life changes that can protect their families and society as a whole.

The mainstream media not only downplayed Covid-19 to pitch Trump as xenophobic & neurotic, but after the most important story they got entirely wrong was revealed as the disaster it was, they also warned about the wrong people hoarding much needed supplies.

If people would have rushed to buy masks in January it would have sent the market signal to make more. Virtue signaling was considered more important than life.

Instead of any attempts at truth we got communist-fed false assurances to provide the illusion of stability. Lives lack value when compared against maintaining political power:

In 1989, when Chinese citizens raised a Goddess of Democracy on Tiananmen Square, some pinned their hopes on the People’s Liberation Army: Surely the people’s army would never fire on the people. In fact, PLA soldiers proved quite adept at firing on the people. And to this day Beijing refuses to come clean about how many it killed at Tiananmen.
...
Communism has always been far more about Lenin than Marx—that is, about getting and holding power, rather than any economic arrangement. And it’s extraordinary how consistent the lies and violence have been across time and geography, given the many different flavors of communism.

Fake News About Fake News

As China was lying to the world, setting hundreds of thousands of people up for death & destroying the global economy, we suggested the problem was not lies from the CCP or the disease that spread globally in part due to their lies, but rather we should fight "fake news"

The rise of “fake news” - including misinformation and inaccurate advice on social media - could make disease outbreaks such as the COVID-19 coronavirus epidemic currently spreading in China worse, according to research published on Friday.

The WHO shills for the CCP:

The lengths to which the WHO went to sacrifice its scientific- and health-related mission for political considerations relating to China were at times both absurd and trivial. For example, in the Coronavirus Q&A that was first posted to its website, the WHO maintained multiple versions. The original English language version of the Q&A counseled that there were four common myths about preventing or curing a COVID-19 infection: smoking, wearing multiple masks, taking antibiotics, and traditional herbal remedies. The original Chinese version omitted ‘traditional herbal remedies’ as a myth. Then the WHO took down ‘traditional herbal remedies’ in both languages. Politics over health. Politics over science. At even the smallest, silliest level.

As the WHO praises the CCP we learn fake news is anything which counters the WHO.

And to protect people globally and fight sources of fake news Google is working with ... the WHO:

WHO is also battling misinformation, working with Google to ensure that people get facts from the U.N. health agency first when they search for information about the virus. Social media platforms such as Twitter, Facebook, Tencent and TikTok have also taken steps to limit the spread of misinformation and rumors about the outbreak.

YouTube is also removing medically substantiated content about coronavirus.

Even the China Uncensored video about the CCP's coverup has a COVID-19 learn more banner redirecting attention back to official sources.

Now there are some horrible and ridiculous official statements being made & a whole bunch of crazies spreading "eat aquarium cleaner, protect yourself from COVID-19." I even read a story about a guy who committed suicide because he feared he had COVID-19. All that stuff is horrible, but any and all attempts to defuse those horrible issues & clean them up should come with a note about how the CCP lied broadly, extensively, and is to not be trusted in any

Increasing Time on Site

Aaron Wall — Fri, 24 Apr 2020 07:03:26 -0700

Changing User Intents

Google's search quality rater document highlights how the intent of searches can change over time for a specific keyword.

A generic search for [iPhone] is likely to be related to the most recent model. A search for [President Bush] likely was related to the 41st president until his son was elected & then it was most likely to be related to 43.

Faster Ranking Shifts

About 17 years ago when Google was young they did monthly updates where most of any ranking signal shift that would happen would get folded into the rankings. The web today is much faster in terms of the rate of change, amount of news consumption, increasing political polarization, social media channels that amplify outrage and how quickly any cultural snippet can be taken out of context.

Yesterday President Trump had some interesting stuff to say about bleach. In spite of there being an anime series by the same name, news coverage of the presser has driven great interest in the topic.

And that interest is already folded into the organic search results through Google News insertion, Twitter tweet insertion, and the query deserves freshness (QDF) algorithm driving insertion of news stories in other organic search ranking slots.

If a lot of people are searching for something and many trusted news organizations are publishing information about a topic then there is little risk in folding fresh information into the result set.

Temporary Versus Permanent Change

When the intent of a keyword changes sometimes the change is transitory & sometimes it is not.

One of the most common ad-driven business models online is to take something that was once paid, make it free, and then layer ads or some other premium features on top to monetize a different part of the value chain. TripAdvisor democratized hotel reviews. Zillow made foreclosure information easily accessible for free, etc.

The success of remote working & communication services like Skype, Zoom, Basecamp, Slack, Trello, and the ongoing remote work experiment the world is going through will permanently change some consumer behaviors & how businesses operate.

A Pew survey mentioned 43% of Americans stated someone in their house recently lost their job, had their hours reduced, and/or took pay cuts. Hundreds of thousands of people are applying to work in Amazon's grueling fulfillment centers.

To many of these people a lone wolf online job would be a dream come true.

If you had a two hour daily commute and were just as efficient working at home most days would you be in a rush to head back to the office?

How many former fulltime employees are going to become freelancers building their own small businesses they work on directly while augmenting it with platform work on other services like Uber, Lyft, DoorDash, Upwork, Fiverr, 99 Designs, or even influencer platforms like Intellifluence?

If big publishers are getting disintermediated by monopoly platforms & ad networks are offering crumbs of crumbs there's no harm in selling custom ads directly or having your early publishing efforts subsidized through custom side deals as you build market awareness and invest into building other products and services to sell.

Wordpress keeps adding more features. Many technology services like Shopify, Stripe & Twilio are making most parts of the tech stack outside of marketing cheaper & easier to scale.

As technology improves, we spend more time online, more activities happen online, and more work becomes remote. All this leads to the distinction between online and offline losing meaning other than perhaps in terms of cost structure & likelihood of bankruptcy.

Before Panda / After Panda

Before the Panda update each additional page which was created was another lotto ticket and a chance to win. If users had a crappy user experience on a page or site maybe you didn't make the sale, but if the goal of the page was to have the content so crappy that ads were more appealing that could lead to fantastic monetization while it lasted.

That strategy worked well for eHow, fueling the pump-n-dump Demand Media IPO.

Demand Media had to analyze eHow and pay to delete over a million articles which they deemed to have a negative economic value in the post-Panda world.

After the Panda update having many thin pages laying around and creating more thin pages was layering risk on top of risk. It made sense to shift to a smaller, tighter, deeper & more differentiated publishing model.

Entropy & Decay

The web goes through a constant state of reinvention.

Old YouTube Flash embeds break.

HTTP content calls in sites that were upgraded to HTTPS break.

Software which is not updated has security exploits.

If you have a large website and do not regularly update where you are linking to your site is almost certainly linking to porn and malware sites somewhere.

As users shifted to mobile websites that ignored mobile interfaces became relatively less appealing.

Changing web browser behaviors can break website logins and how data is shared across websites dependent on third party services.

Competition improves.

Algorithms change.

Ads eat a growing share of real estate on dominant platforms while organic reach slides.

Everything on the web is constantly dying as competition improves, technology changes and language gets redefined.

Staying Relevant

Even if a change in user intent is transitory, in some cases it can make sense to re-work a page to address a sudden surge of interest to improve time on site, user engagement metrics & make the content on your page more citation-worthy. If news writers are still chasing a trend then having an in-depth background piece of content with more depth gives them something they may want to link at.

Since the Covid-19 implosion of the global economy came into effect I've seen two different clients have a sort of sudden surge in traffic which would make little to no sense unless one considered currently spreading news stories.

News coverage creates interest in topics, shapes perspectives of topics, and creates demand for solutions.

If you read the right people on Twitter sometimes you can be days, weeks or even months ahead of the broader news narrative. Some people are great at spotting the second, third and fourth order effects of changes. You can spot stories bubbling up and participate in the trends.

An Accelerating Rate of Change

When the web was slower & easier you could find an affiliate niche and succeed in it sometimes for years before solid competition would arrive. One of the things I was most floored about this year from a marketing perspective was how quickly spammers ramped up a full court press amplifying the fear the news media was pitching. I think I get something like a hundred spam emails a day pitching facemasks and other COVID-19 solutions. I probably see 50+ other daily ads from services like Outbrain & similar.

The web moves so much faster that the SEC is already taking COVID-19 related actions against dozens of companies. Google banned advertising protective masks and recently announced they are rolling out advertiser ID verification to increase transparency.

If Google is looking at their advertisers with a greater degree of suspicion even into an economic downturn when Expedia is pulling $4 billion from their ad budget & Amazon is cutting back on their Google ad budget and Google decides to freeze hiring then it makes far more sense to keep reinvesting into improving any page which is getting a solid stream of organic search traffic.

Company Town

After Amazon cut their Google ad budget in March Google decided to expand Google Shopping to include free listings. When any of the platforms is losing badly they can afford to subsidize that area and operate it at a loss to try to gain marketshare while making the dominant player in that category look more extreme.

When a player is dominant in a category they can squeeze down on partners. Amazon once again cut affiliate payouts and the Wall Street Journal published an article citing 20 current and former Amazon insiders who stated Amazon uses third party merchant sales data to determine which products to clone:

Amazon employees accessed documents and data about a bestselling car-trunk organizer sold by a third-party vendor. The information included total sales, how much the vendor paid Amazon for marketing and shipping, and how much Amazon made on each sale. Amazon’s private-label arm later introduced its own car-trunk organizers. ... Amazon’s private-label business encompasses more than 45 brands with some 243,000 products, from AmazonBasics batteries to Stone & Beam furniture. Amazon says those brands account for 1% of its $158 billion in annual retail sales, not counting Amazon’s devices such as its Echo speakers, Kindle e-readers and Ring doorbell cameras.

Amazon does not even need to sell their private label products to shift their economics. As Amazon clones products they force the branded ad buy for a company to show up for their own branded terms, taking another bite out of the partner: "Fortem spends as much as $60,000 a month on Amazon advertisements for its items to come up at the top of searches, said Mr. Maslakou."

Amazon has grown so dominant they've not only cut their affiliate & search advertising while hiring hundreds of thousands of employees, but they've also dramatically slowed down shipping times while pulling back on their on-site people also purchase promotions to get users to order less.

While they are growing stronger department stores and other legacy retailers are careening toward bankruptcy.

Multiple Ways to Improve

If you have a page which is ranking that gets a sudden spike in traffic it makes a lot of sense to consider current news & try to consider if the intent of the searcher has changed. If it has, address it as best you can in the most relevant way possible, even if the change is temporary, then consider switching back to the old version of the page or reorganizing your content if/when/as the trend has passed.

One of the pages mentioned above was a pre-Panda "me too" type page which was suddenly flooded with thousands of user visitors. A quality inbound link can easily cost $100 to multiples of that. If a page is already getting thousands of visitors, why not invest a couple hundred dollars into dramatically improving it, knowing that some of those drive by users will likely eventually share it? Make the page an in-depth guide with great graphics and some of those 10,000's of visitors will eventually link to it, as they were already interested in the topic, the page already gets a great stream of traffic, and the content quality is solid.

Last week a client had a big spike from a news topic that changed the intent of a keyword. Their time on site from those visitors was under a minute. After the page was re-created to reflect changing consumer intent their time on site jumped to over 3 minutes for users entering that page. Those users had a far lower bounce rate, a far better user experience, are going to be more likely to trust the site enough to seek it out again, and this sends a signal to Google that the site is still maintained & relevant to the modern search market.

There are many ways to chase the traffic stream

create new content on new pages
gut the old page & publish entirely new content
re-arrange the old page while publishing new relevant breaking news at the top

In general I think the third option is often the best approach because you are aligning the page which already sees the traffic stream with the content they are looking for, while also ensuring any users from the prior intent can still access what they are looking for.

If the trend is huge, or the change in intent is permanent then you could also move the old content to a legacy URL archived page while making the high-traffic page focus on the spiking news topic.

The above advice applies to pages which rank for keywords that change in intent, but it can also apply to any web page which has a strong flow of user traffic. Keep improving the things people see most because improvements there have the biggest returns. How can you make a page deeper, better, more differentiated from the rest of the web?

Does Usage Data Matter?

Objectively, if people visit your website and do not find what they were looking for they are going to click the back button and be done with you.

Outdated content that has become irrelevant due to changing user tastes is only marginally better than outright spam.

While Google suggests they largely do not use bounce rate or user data in their rankings, they have also claimed end user data was the best way they could determine if the user was satisfied with a particular search result. Five years ago Bill Slawski wrote a blog post about long clicks which quoted Steven Levy's In The Plex book:

"On the most basic level, Google could see how satisfied users were. To paraphrase Tolstoy, happy users were all the same. The best sign of their happiness was the "Long Click" — This occurred when someone went to a search result, ideally the top one, and did not return. That meant Google has successfully fulfilled the query."

Think of how many people use the Chrome web browser or have Android tracking devices on them all hours of the day. There is no way Google would be able to track those billions of users every single day without finding a whole lot of signal in the noise.

Categories:

publishing & media

Revenue Quality & Leverage

Aaron Wall — Tue, 17 Mar 2020 04:07:05 -0700

The coronavirus issue is likely to linger for some time.

GERMANY PUBLIC HEALTH AGENCY PRESIDENT SAYS OUR ASSUMPTION IS THAT IT WILL TAKE ABOUT TWO YEARS FOR THIS PANDEMIC TO RUN ITS COURSE— Quantitative Trading (@fiquant) March 17, 2020

Up to 70% of Germany could become infected & some countries like the UK are even considering herd immunity as a strategy:

"I’m an epidemiologist. When I heard about Britain’s ‘herd immunity’ coronavirus plan, I thought it was satire"
- William Hanage

What if their models are broken?

Many companies like WeWork or Oyo have been fast and loose chasing growth while slower growing companies have been levering up to fund share buybacks. Airlines spent 96% of free cash flow on share buybacks. The airlines seek a $50 billion bailout package.

There are knock-on effects from Boeing to TripAdvisor to Google all the way down to travel affiliate blogger, local restaurants closing, the over-levered bus company going through bankruptcy & bondholders eating a loss on the debt.

Companies are going to let a lot of skeletons out of the closet as literally anything and everything bad gets attributed to coronavirus. Layoffs, renegotiating contracts, pausing ad budgets, renegotiating debts, requesting bailouts, etc. The Philippine stock market was recently trading at 2012 levels & closed indefinitely.

Brad Geddes mentioned advertisers have been aggressively pulling PPC budgets over the past week: “If you have to leave the house to engage in the service, it just seems like it’s not converting right now.”

During the prior recession Google repriced employee options to retain talent.

More time online might mean search engines & social networks capture a greater share of overall ad spend, but if large swaths of the economy do not convert & how people live changes for an extended period of time it will take time for the new categories to create the economic engines replacing the old out-of-favor categories.

[IMPORTANT: insert affiliate ad for cruise vacations here]

As Google sees advertisers pause ad budgets Google will get more aggressive with keeping users on their site & displacing organic click flows with additional ad clicks on the remaining advertisers.

When Google or Facebook see a 5% or 10% pullback other industry players might see a 30% to 50% decline as the industry pulls back broadly, focuses more resources on the core, and the big attention merchants offset their losses by clamping down on other players.

At its peak TripAdvisor was valued at about $14 billion & it is now valued at about $2 billion.

TripAdvisor announced layoffs. As did Expedia. As did Booking.com. As did many hotels. And airlines. etc. etc. etc.

I am not suggesting people should be fearful or dominated by negative emotions. Rather one should live as though many other will be living that way.

In times of elevated uncertainty, in business it is best to not be led by emotions unless they are positive ones. Spend a bit more time playing if you can afford to & work more on things you love.

Right now we might be living through the flu pandemic of 1918 and the Great Depression of 1929 while having constant access to social media updates. And that's awful.

Consume less but deeper. Less Twitter, less news, fewer big decisions, read more books.

It is better to be more pragmatic & logic-based in determining opportunity cost & the best strategy to use than to be led by extreme fear.

If you have sustainable high-margin revenue treasure it.
If you have low-margin revenue it might quickly turn into negative margin revenues unless something changes quickly.
If you have low-margin revenue which is sustainable but under-performed less stable high-margin revenues you might want to put a bit more effort into those sorts of projects as they are more likely to endure.

On a positive note, we might soon get a huge wave of innovation...

"Take the Great Depression. Economist Alexander Field writes that “the years 1929–1941 were, in the aggregate, the most technologically progressive of any comparable period in U.S. economic history.” Productivity growth was twice as fast in the 1930s as it was in the decade prior. The 1920s were the era of leisure because people could afford to relax. The 1930s were the era of frantic problem solving because people had no other choice. The Great Depression brought unimaginable financial pain. It also brought us supermarkets, microwaves, sunscreen, jets, rockets, electron microscopes, magnetic recording, nylon, photocopying, teflon, helicopters, color TV, plexiglass, commercial aviation, most forms of plastic, synthetic rubber, laundromats, and countless other discoveries."

The prior recession led to trends like Groupon. The McJobs recovery led to services like Uber & DoorDash. Food delivery has been trending south recently, though perhaps the stay-at-home economy will give it a boost.

I have been amazed at how fast affiliates moved with pushing N95 face masks online over the past couple months. Seeing how fast that stuff spun up really increases the perceived value of any sustainable high-margin businesses.

Amazon.com is hiring another 100,000 warehouse workers as people shop from home. Amazon banned new face masks and hand sanitizer listings. One guy had to donate around 18,000 cleaning products he couldn't sell.

I could see online education becoming far more popular as people aim to retrain while stuck at home.

What sorts of new industries will current & new technologies lead to as more people spend time working from home?

Categories:

publishing & media

Subscription Fatigue

Aaron Wall — Sat, 08 Feb 2020 08:27:58 -0800

Subscription Management

I have active subscriptions with about a half-dozen different news & finance sites along with about a half dozen software tools, but sometimes using a VPN or web proxy across different web browsers makes logging in to all of them & clearing cookies for some paywall sites a real pain.

If you don't subscribe to any outlets then subscribing to an aggregator like Apple News+ can make a lot of sense, but it is very easy to end up with dozens of forgotten subscriptions.

Subscription fatigue is turning into subscription stress. Something alarming, guilt inducing about having 40+ reoccurring charges each month. Financial death by a thousand cuts.— Tom Goodwin (@tomfgoodwin) January 28, 2020

Winner-take-most Market Stratification

The news business is coming to resemble other tech-enabled businesses where a winner takes most. The New York Times stock, for instance, is trading at 15 year highs & they recently announced they are raising subscription prices:

The New York Times is raising the price of its digital subscription for the first time, from $15 every four weeks to $17 — from about $195 to $221 a year.

With a Trump re-election all but assured after the Russsia, Russia, Russia garbage, the party-line impeachment (less private equity plunderer Mitt Romney) & the ridiculous Iowa primary, many NYT readers will pledge their #NeverTrumpTwice dollars with the New York Times.

If you think politics looks ridiculous today, wait until you see some of the China-related ads in a half-year as the 2019 novel coronavirus spreads around the world.

Police in Central China's Wuhan arrested 8 people spreading rumors about local outbreak of unidentifiable #pneumonia. Previous online posts said it was SARS. https://t.co/oVpk4EIYM7 pic.twitter.com/JXbK9pmq8v— Global Times (@globaltimesnews) January 1, 2020

Arresting a doctor who warned about the outbreak doesn't have good optics, particularly after hundreds of other deaths piled up from it & when he later died from from the virus.

The optics keep getting worse.

Somewhere in Wuhan, three unknown people are wearing protective clothing but holding guns @SolomonYue #China_is_terrorist pic.twitter.com/cq28z0sPiF— 港英漁業 (@lym104_hker) February 1, 2020

How does a broad-based news site compete with the user generated Tweets in such a zone?

WATCH: Chinese authorities are now WELDING DOORS SHUT to whole apartment buildings, as well as residents inside - to impose #Coronavirus quarantine. #Wuhan pic.twitter.com/feclKG90pC— AS-Source News (@ASBreakingNews) February 8, 2020

And any widely known individual journalist who builds a large audience might get disappeared.

Twitter recently surpassed $1 billion in quarterly revenues, but time spent on Twitter is time not spent on other news websites.

Outside of a few core winners, the news business online has been so brutal that even Warren Buffett is now a seller. As the economics get uglier news sites get more extreme with ad placements, user data sales, and pushing subscriptions. Some of these aggressive monetization efforts make otherwise respectable news outlets look like part of a very downmarket subset of the web.

Users Fight Back

Users have thus adopted to blocking ads & are also starting to ramp up blocking paywall notifications.

Some of the most popular browser extensions are ad blockers & tracking blockers like Adblock Plus, Ghostery & Privacy Badger.
Apple has made tracking their users across sites harder with their Intelligent Tracking Prevention, causing iPhone ad rates to plummet: "The allure of a Safari user in an auction has plummeted," Rubicon Project CEO Michael Barrett told the publication. "There's no easy ability to ID a user."
The Opera web browser comes with an ad blocker baked in.
Mozilla is also pushing to protect user privacy in Firefox.
Google recently announced they will stop supporting third party cookies in Chrome in the next couple years. Those who invested into adopting AMP will have to invest into making yet more technical changes to manage paywalls on AMP pages.

Each additional layer of technological complexity is another cost center publishers have to fund, often through making the user experience of their sites worse, which in turn makes their own sites less differentiated & inferior to the copies they have left across the web (via AMP, via Facebook Instant Articles, syndication in Apple News or on various portal sites like MSN or Yahoo!).

A Web Browser For Every Season

Google Chrome is spyware, so I won't recommend installing that.

Not good enough for you? Not a direct enough corollary? How about this?Also out today: https://t.co/6dUWCCEyii Google has a backdoor to track individual Chrome users by installation ID.Even GG's denial admits pieces of the same complaints y'all had about Jumpshot last week! pic.twitter.com/Km2mQfOgbJ— Rand Fishkin (@randfish) February 4, 2020

Here Google's official guide on how to remove the spyware.

The easiest & most basic solution which works across many sites using metered paywalls is to have multiple web browsers installed on your computer. Have a couple browsers which are used exclusively for reading news articles when they won't show up in your main browser & set those web browsers to delete cookies on close. Or open the browsers in private mode and search for the URL of the page from Google to see if that allows access.

If you like Firefox there are other iterations from other players like Pale Moon, Comodo IceDragon or Waterfox using their core.
If you like Google Chrome then Chromium is the parallel version of it without the spyware baked in. The Chromium project is also the underlying source used to build about a dozen other web browsers including: Opera, Vivaldi, Brave, Cilqz, Blisk, Comodo Dragon, SRWare Iron, Yandex Browser & many others. Even Microsoft recently switched their Edge browser to being powered by the Chromium project. The browsers based on the Chromium store allow you to install extensions from the Chrome web store.
Some web browsers monetize users by setting affiliate links on the home screen and/or by selling the default search engine recommendation. You can change those once and they'll typically stick with whatever settings you use.
For some browsers I use for regular day to day web use I set them up to continue session on restart, and I have a session manager plugin like this one for Firefox or this one for Chromium-based browsers. For browsers which are used exclusively for reading paywall blocked articles I set them up to clear cookies on restart.

Bypassing Paywalls

There are a couple solid web browser plugins built specifically for bypassing paywalls.

Academic Journals

Unpaywall is an open database of around 25,000,000 free scholarly articles. They provide extensions for Firefox and Chromium based web browsers on their website.

News Articles

There is also one for news publications called bypass paywalls.

Mozilla Firefox: To install the Firefox version go here.
Chrome-like web browsers: To install the Chrome version of the extension in Opera or Chromium or Microsoft Edge you can download the extension here, enter developer mode inside the extensions area of your web browser & install extension. To turn developer mode on, open up the drop down menu for the browser, click on extensions to go to the extension management area, and then slide the "Developer mode" button to the right so it is blue.

Regional Blocking

If you travel internationally some websites like YouTube or Twitter or news sites will have portions of their content restricted to only showing in some geographic regions. This can be especially true for new sports content and some music.

These can be bypassed by using a VPN service like NordVPN, ExpressVPN, Witopia or IPVanish. Some VPN providers also sell pre-configured routers. If you buy a pre-configured router you can use an ethernet switch or wifi to switch back and forth between the regular router and the VPN router.

You can also buy web proxies & enter them into the Foxy Proxy web browser extension (Firefox or Chromium-compatible) with different browsers set to default to different country locations, making it easier to see what the search results show in different countries & cities quickly.

If you use a variety of web proxies you can configure some of them to work automatically in an open source rank tracking tool like Serposcope.

The Future of Journalism

I think the future of news is going to be a lot more sites like Ben Thompson's Stratechery or Jessica Lessin's TheInformation & far fewer broad/horizontal news organizations. Things are moving toward the 1,000 true fans or perhaps 100 true fans model:

This represents a move away from the traditional donation model—in which users pay to benefit the creator—to a value model, in which users are willing to pay more for something that benefits themselves. What was traditionally dubbed “self-help” now exists under the umbrella of “wellness.” People are willing to pay more for exclusive, ROI-positive services that are constructive in their lives, whether it’s related to health, finances, education, or work. In the offline world, people are accustomed to hiring experts across verticals

A friend of mine named Terry Godier launched a conversion-oriented email newsletter named Conversion Gold which has done quite well right out of the gate, leading him to launch IndieMailer, a community for paid newsletter creators.

The model which seems to be working well for those sorts of news sites is...

stick to a tight topic range
publish regularly at a somewhat decent frequency like daily or weekly, though have a strong preference to quality & originality over quantity
have a single author or a small core team which does most the writing and expand editorial hiring slowly
offer original insights & much more depth of coverage than you would typically find in the mainstream news
Rely on Wordpress or a low-cost CMS & billing technology partner like Substack, Memberful, sell on a marketplace like Udemy, Podia or Teachable, or if they have a bit more technical chops they can install aMember on their own server. One of the biggest mistakes I made when I opened up a membership site about a decade back was hand rolling custom code for memberhsip management. At one point we shut down the membership site for a while in order to allow us to rip out all that custom code & replace it with aMember.
Accept user comments on pieces or integrate a user forum using something like Discord on a subdomain or a custom Slack channel. Highlight or feature the best comments. Update readers to new features via email.
Invest much more into obtaining unique data & sources to deliver new insights without spending aggressively to syndicate onto other platforms using graphical content layouts which would require significant design, maintenance & updating expenses
Heavily differentiate your perspective from other sources
maintain a low technological maintenance overhead
low cost monthly subscription with a solid discount for annual pre-payment
instead of using a metered paywall, set some content to require payment to read & periodically publish full-feature free content (perhaps weekly) to keep up awareness of the offering in the broader public to help offset churn.

Some also work across multiple formats with complimentary offerings. The Ringer has done well with podcasts & Stratechery also has the Exponent podcast.

There are a number of other successful online-only news subscription sites like TheAthletic & Bill Bishop's Sinocism newsletter about China, but I haven't subscribed to them yet. Many people support a wide range of projects on platforms like Patreon & sites like MasterClass with an all-you-can-eat subscription will also make paying for online content far more common..

Categories:

publishing & media

Favicon SEO

Aaron Wall — Sun, 19 Jan 2020 08:25:10 -0800

Google recently copied their mobile result layout over to desktop search results. The three big pieces which changed as part of that update were

URLs: In many cases Google will now show breadcrumbs in the search results rather than showing the full URL. The layout no longer differentiates between HTTP and HTTPS. And the URLs shifted from an easily visible green color to a much easier to miss black.
Favicons: All listings now show a favicon next to them.
Ad labeling: ad labeling is in the same spot as favicons are for organic search results, but the ad labels are a black which sort of blends in to the URL line. Over time expect the black ad label to become a lighter color in a way that parallels how Google made ad background colors lighter over time.

Last year, our search results on mobile gained a new look. That’s now rolling out to desktop results this week, presenting site domain names and brand icons prominently, along with a bolded “Ad” label for ads. Here’s a mockup: pic.twitter.com/aM9UAbSKtv— Google SearchLiaison (@searchliaison) January 13, 2020

One could expect this change to boost the CTR on ads while lowering the CTR on organic search results, at least up until users get used to seeing favicons and not thinking of them as being ads.

The Verge panned the SERP layout update. Some folks on Reddit hate this new layout as it is visually distracting, the contrast on the URLs is worse, and many people think the organic results are ads.

Conspiracy Theory: The REAL reason icons are in SERPs is to encourage "banner blindness" for the "Ad" text. Once people see the icons over and over, they will learn to mentally ignore the top left. pic.twitter.com/LaXdZjNLK1— Rishi Lakhani (@rishil) January 17, 2020

I suspect a lot of phishing sites will use subdomains patterned off the brand they are arbitraging coupled with bogus favicons to try to look authentic. I wouldn't reconstruct an existing site's structure based on the current search result layout, but if I were building a brand new site I might prefer to put it at the root instead of on www so the words were that much closer to the logo.

Google provides the following guidelines for favicons

Both the favicon file and the home page must be crawlable by Google (that is, they cannot be blocked to Google).
Your favicon should be a visual representation of your website's brand, in order to help users quickly identify your site when they scan through search results.
Your favicon should be a multiple of 48px square, for example: 48x48px, 96x96px, 144x144px and so on. SVG files, of course, do not have a specific size. Any valid favicon format is supported. Google will rescale your image to 16x16px for use in search results, so make sure that it looks good at that resolution. Note: do not provide a 16x16px favicon.
The favicon URL should be stable (don’t change the URL frequently).
Google will not show any favicon that it deems inappropriate, including pornography or hate symbols (for example, swastikas). If this type of imagery is discovered within a favicon, Google will replace it with a default icon.

In addition to the above, I thought it would make sense to provide a few other tips for optimizing favicons.

Keep your favicons consistent across sections of your site if you are trying to offer a consistent brand perception.
In general, less is more. 16x16 is a tiny space, so if you try to convey a lot of information inside of it, you'll likely end up creating a blob that almost nobody but you recognizes.
It can make sense to include the first letter from a site's name or a simplified logo widget as the favicon, but it is hard to include both in a single favicon without it looking overdone & cluttered.
A colored favicon on a white background generally looks better than a white icon on a colored background, as having a colored background means you are eating into some of the scarce pixel space for a border.
Using a square shape versus a circle gives you more surface area to work with.
Even if your logo has italics on it, it might make sense to avoid using italics in the favicon to make the letter look cleaner.

Here are a few favicons I like & why I like them:

Citigroup - manages to get the word Citi in there while looking memorable & distinctive without looking overly cluttered
Nerdwallet - the N makes a great use of space, the colors are sharp, and it almost feels like an arrow that is pointing right
Inc - the bold I with a period is strong.
LinkedIn - very memorable using a small part of the word from their logo & good color usage.

Some of the other memorable ones that I like include: Twitter, Amazon, eBay, Paypal, Google Play & CNBC.

Here are a few favicons I dislike & why

Wikipedia - the W is hard to read.
USAA - they included both the logo widget and the 4 letters in a tiny space.
Yahoo! - they used inconsistent favicons across their sites & use italics on them. Some of the favicons have the whole word Yahoo in them while the others are the Y! in italics.

If you do not have a favicon Google will show a dull globe next to your listing. Real Favicon Generator is a good tool for creating favicons in various sizes.

What favicons do you really like? Which big sites do you see that are doing it wrong?

Categories:

seo tips

Brands vs Ads

Aaron Wall — Fri, 08 Nov 2019 08:16:17 -0800

About 7 years ago I wrote about how the search relevancy algorithms were placing heavy weighting on brand-related signals after Vince & Panda on the (half correct!) presumption that this would lead to excessive industry consolidation which in turn would force Google to turn the dials in the other direction.

My thesis was Google would need to increasingly promote some smaller niche sites to make general web search differentiated from other web channels & minimize the market power of vertical leading providers.

The reason my thesis was only half correct (and ultimately led to the absolutely wrong conclusion) is Google has the ability to provide the illusion of diversity while using sort of eye candy displacement efforts to shift an increasing share of searches from organic to paid results.

As long as any market has at least 2 competitors in it Google can create a "me too" offering that they hard code front & center and force the other 2 players (along with other players along the value chain) to bid for marketshare. If competitors are likely to complain about the thinness of the me too offering & it being built upon scraping other websites, Google can buy out a brand like Zagat or a data supplier like ITA Software to undermine criticism until the artificially promoted vertical service has enough usage that it is nearly on par with other players in the ecosystem.

Google need not win every market. They only need to ensure there are at least 2 competing bids left in the marketplace while dialing back SEO exposure. They can then run other services to redirect user flow and force the ad buy. They can insert their own bid as a sort of shill floor bid in their auction. If you bid below that amount they'll collect the profit through serving the customer directly, if you bid above that they'll let you buy the customer vs doing a direct booking.

Where this gets more than a bit tricky is if you are a supplier of third party goods & services where you buy in bulk to get preferential pricing for resale. If you buy 100 rooms a night from a particular hotel based on the presumption of prior market performance & certain channels effectively disappear you have to bid above market to sell some portion of the rooms because getting anything for them is better than leaving them unsold.

Dipping a bit back into history here, but after Groupon said no to Google's acquisition offer Google promptly partnered with players 2 through n to ensure Groupon did not have a lasting competitive advantage. In the fullness of time most those companies died, LivingSocial was acquired by Groupon for nothing & Groupon is today worth less than the amount they raised in VC & IPO funding.

Most large markets will ultimately consolidate down to a couple players (e.g. Booking vs Expedia) while smaller players lack the scale needed to have the economic leverage to pay Google's increasing rents.

This sort of consolidation was happening even when the search results were mostly organic & relevancy was driven primarily by links. As Google has folded in usage data & increased ad load on the search results it becomes harder for a generically descriptive domain name to build brand-related signals.

It is not only generically descriptive sorts of sites that have faded though. Many brand investments turned out to be money losers after the search result set was displaced by more ads (& many brand-related search result pages also carry ads above the organic results).

The ill informed might write something like this:

Since the Motorola debacle, it was Google's largest acquisition after the $676 million purchase of ITA Software, which became Google Flights. (Uh, remember that? Does anyone use that instead of Travelocity or one of the many others? Neither do I.)

The reality is brands lose value as the organic result set is displaced. To make the margins work they might desperately outsource just about everything but marketing to a competitor / partner, which will then latter acquire them for a song.

Travelocity had roughly 3,000 people on the payroll globally as recently as a couple of years ago, but the Travelocity workforce has been whittled to around 50 employees in North America with many based in the Dallas area.

The best relevancy algorithm in the world is trumped by preferential placement of inferior results which bypasses the algorithm. If inferior results are hard coded in placements which violate net neutrality for an extended period of time, they can starve other players in the market from the vital user data & revenues needed to reinvest into growth and differentiation.

Value plays see their stocks crash as growth slows or goes in reverse. With the exception of startups frunded by Softbank, growth plays are locked out of receiving further investment rounds as their growth rate slides.

Startups like Hipmunk disappear. Even an Orbitz or Travelocity become bolt on acquisitions.

The viability of TripAdvisor as a stand alone business becomes questioned, leading them to partner with Ctrip.

TripAdvisor has one of the best link profiles of any commercially oriented website outside of perhaps Amazon.com. But ranking #1 doesn't count for much if that #1 ranking is below the fold.

TripAdvisor shifted their business model to allow direct booking to better monetize mobile web users, but as Google has ate screen real estate and grew Google Travel into a $100 billion business other players have seen their stocks sag.

Google sits at the top of the funnel & all other parts of the value chain are compliments to be commoditized.

Buy premium domain names? Google's SERPs test replacing domain names with words & make the domain name gray.
Improve conversion rates? Your competitor almost certainly did as well, now you both can bid more & hand over an increasing economic rent to Google.
Invest in brand awareness? Google shows ads for competitors on your brand terms, forcing you to buy to protect the brand equity you paid to build.

Search Metrics mentioned Hotels.com was one of the biggest losers during the recent algorithm updates: "I’m going to keep on this same theme there, and I’m not going to say overall numbers, the biggest loser, but for my loser I’m going to pick Hotels.com, because they were literally like neck and neck, like one and two with Booking, as far as how close together they were, and the last four weeks, they’ve really increased that separation."

As Google ate the travel category the value of hotel-related domain names has fallen through the floor.

Most of the top selling hotel-related domain names were sold about a decade ago:

On August 8th HongKongHotels.com sold for $4,038. And the buyer may have overpaid for it!

Google consistently grows their ad revenues 20% a year in a global economy growing at under 4%.

There are only about 6 ways they can do that

growth of web usage (though many of those who are getting online today have a far lower disposable income than those who got on a decade or two ago did)
gain marketshare (very hard in search given that they effectively are the market in most markets outside of China & Russia)
create new inventory (new ad types on Google Maps & YouTube)
charge more for clicks
improve at targeting by better surveillance of web users (getting harder after GDPR & similar efforts from some states in the next year or two)
shift click streams away from organic toward paid channels (through larger ads, more interactive ad units, less appealing organic result formatting, etc.)

Wednesday both Expedia and TripAdvisor reported earnings after hours & both fell off a cliff: "Both Okerstrom and Kaufer complained that their organic, or free, links are ending up further down the page in Google search results as Google prioritizes its own travel businesses."

Losing 20% to 25% of your market cap in a single day is an extreme move for a company worth billions of dollars.

Thursday Google hit fresh all time highs.

"Google’s old motto was ‘Don’t Be Evil’, but you can’t be this big and profitable and not be evil. Evil and all-time highs pretty much go hand in hand." - Howard Lindzon

Booking held up much better than TripAdvisor & Expedia as they have a bigger footprint in Europe (where antitrust is a thing) and they have a higher reliance on paid search versus organic.

The broader SEO industry is to some degree frozen by fear. Roughly half of SEOs claim to have not bought *ANY* links in a half-decade.

Anonymous survey: have you (or your company) purchased backlinks - of ANY quality - for your own site, or any of your clients' sites, at any point in the past ~5 years?— Lily Ray (@lilyraynyc) October 24, 2019

Long after most of the industry has stopped buying links some people still run the "paid links are a potential FTC violation guideline" line as though it is insightful and/or useful.

Some people may be violating FTC rules by purchasing links that are not labeled as sponsored. This includes "content marketers" who publish articles with paid links on sites they curate. It's a ticking time bomb because it's illegal.— Roger Montti (@martinibuster) October 24, 2019

Ask the people carrying Google's water what they think of the official FTC guidance on poor ad labeling in search results and you will hear the beautiful sound of crickets chirping.

Where is the ad labeling in this unit?

Does small gray text in the upper right corner stating "about these results" count as legitimate ad labeling?

And then when you scroll over that gray text and click on it you get "Some of these hotel search results may be personalized based on your browsing activity and recent searches on Google, as well as travel confirmations sent to your Gmail. Hotel prices come from Google's partners."

Zooming out a bit further on the above ad unit to look at the entire search result page, we can now see the following:

4 text ad units above the map
huge map which segments demand by price tier, current sales, luxury, average review, geographic location
organic results below the above wall of ads, and the number of organic search results has been reduced from 10 to 7

How many scrolls does one need to do to get past the above wall of ads?

If one clicks on one of the hotel prices the follow up page is ... more ads.

Check out how the ad label is visually overwhelmed by a bright blue pop over.

Worth noting Google Chrome has a built-in ad blocking feature which allows them to strip all ads from displaying on third party websites if they follow Google's best practices layout used in the search results.

You won't see ads on websites that have poor ad experiences, like:

Too many ads
Annoying ads with flashing graphics or autoplaying audio
Ad walls before you can see content

When these ads are blocked, you'll see an "Intrusive ads blocked" message. Intrusive ads will be removed from the page.

The following 4 are all true:

Google buys entire businesses, guts them & sells them for parts.
Google's core business model is selling paid links with ever lighter disclosure.
Some SEOs suggest selling links or exposure is beneath them.
Ex-Google employees leverage their past gains to buy well linked sites like Money.com.

And, as a bonus, to some paid links are a crime but Google can sponsor academic conferences for market regulators while requesting the payments not be disclosed.

Hotels have been at the forefront of SEO for many years. They drive massive revenues & were perhaps the only vertical ever referenced in the Google rater guidelines which stated all affiliate sites should be labeled as spam even if they are helpful to users.

Google has won most of the profits in the travel market & so they'll need to eat other markets to continue their 20% annual growth.

Some people who market themselves as SEO experts not only recognize this trend but even encourage this sort of behavior:

Zoopla, Rightmove and On The Market are all dominant players in the industry, and many of their house and apartment listings are duplicated across the different property portals. This represents a very real reason for Google to step in and create a more streamlined service that will help users make a more informed decision. ... The launch of Google Jobs should not have come as a surprise to anyone, and neither should its potential foray into real estate. Google will want to diversify its revenue channels as much as possible, and any market that allows it to do so will be in its sights. It is no longer a matter of if they succeed, but when.

The dominance Google has in core profitable vertical markets also exists in the news & general publishing categories. Some publishers get more traffic from Google Discover than from Google search. Inclusion in Google Discover requires using Google's proprietary AMP format.

Publishers which try to turn off Google's programmatic ads find their display ad revenues fall off a cliff:

"Nexstar Media Group Inc., the largest local news company in the U.S., recently tested what would happen if it stopped using Google’s technology to place ads on its websites. Over several days, the company’s video ad sales plummeted. “That’s a huge revenue hit,” said Tony Katsur, senior vice president at Nexstar. After its brief test, Nexstar switched back to Google." ... "Regulators who approved that $3.1 billion deal warned they would step in if the company tied together its offerings in anticompetitive ways. In interviews, dozens of publishing and advertising executives said Google is doing just that with an array of interwoven products."

News is operating like many other (broken) markets. The Salt Lake Tribune converted to a nonprofit organization.

Many local markets have been consolidated down to ownership by a couple private equity shop roll ups looking to further consolidate the market. Gatehouse Media is acquiring Gannett.

The Washington Post - owned by Amazon's Jeff Bezos - is creating an ad tech stack which serves other publishers & brands, though they also believe a reliance on advertiser & subscription revenue is unsustainable: “We are too beholden to just advertiser and subscriber revenue, and we’re completely out of our minds if we think that’s what’s going to be what carries us through the next generation of publishing. That’s very clear.”

We are nearing many inflection points in many markets where markets that seemed somewhat disconnected from search will still end up being dominated by Google. Gmail, Android, Web Analytics, Play Store, YouTube, Maps, Waze ... are all additional points of leverage beyond the core search & ads products.

Google is investing heavily in quantum computing. Google Fiber was a nothingburger to force competing ISPs into accelerating expensive network upgrades, but beaming in internet services from satellites will allow Google to bypass local politics, local regulations & heavy network infrastructure construction costs. A startup named Kepler recently provided high-bandwidth connectivity to the Arctic. When Google launches a free ISP there will be many knock on effects causing partners to long for the day where Google was only as predatory as they are today.

Categories:

google

Internet Wayback Machine Adds Historical TextDiff

Aaron Wall — Mon, 04 Nov 2019 23:36:47 -0800

The Wayback Machine has a cool new feature for looking at the historical changes of a web page.

The color scale shows how much a page has changed since it was last cached & you can select between any two documents to see how a page has changed over time.

You can then select between any two documents to see a side-by-side comparison of the documents.

That quickly gives you an at-a-glance view of how they've changed their:

web design
on-page SEO strategy
marketing copy & sales strategy

For sites that conduct seasonal sales & rely heavily on holiday themed ads you can also look up the new & historical ad copy used by large advertisers using tools like Moat, WhatRunsWhere & Adbeat.

Categories:

seo tools

Dofollow, Nofollow, Sponsored, UGC

Aaron Wall — Wed, 23 Oct 2019 22:20:14 -0700

A Change to Nofollow

Last month Google announced they were going to change how they treated nofollow, moving it from a directive toward a hint. As part of that they also announced the release of parallel attributes rel="sponsored" for sponsored links & rel="ugc" for user generated content in areas like forums & blog comments.

Why not completely ignore such links, as had been the case with nofollow? Links contain valuable information that can help us improve search, such as how the words within links describe content they point at. Looking at all the links we encounter can also help us better understand unnatural linking patterns. By shifting to a hint model, we no longer lose this important information, while still allowing site owners to indicate that some links shouldn’t be given the weight of a first-party endorsement.

In many emerging markets the mobile web is effectively the entire web. Few people create HTML links on the mobile web outside of on social networks where links are typically nofollow by default. This reduces the potential signal available to either tracking what people do directly and/or shifting how the nofollow attribute is treated.

Google shifting how nofollow is treated is a blanket admission that Penguin & other elements of "the war on links" were perhaps a bit too effective and have started to take valuable signals away from Google.

Google has suggested the shift in how nofollow is treated will not lead to any additional blog comment spam. When they announced nofollow they suggested it would lower blog comment spam. Blog comment spam remains a growth market long after the gravity of the web has shifted away from blogs onto social networks.

Changing how nofollow is treated only makes any sort of external link analysis that much harder. Those who specialize in link audits (yuck!) have historically ignored nofollow links, but now that is one more set of things to look through. And the good news for professional link auditors is that increases the effective cost they can charge clients for the service.

Some nefarious types will notice when competitors get penalized & then fire up Xrummer to help promote the penalized site, ensuring that the link auditor bankrupts the competing business even faster than Google.

Links, Engagement, or Something Else...

When Google was launched they didn't own Chrome or Android. They were not yet pervasively spying on billions of people:

If, like most people, you thought Google stopped tracking your location once you turned off Location History in your account settings, you were wrong. According to an AP investigation published Monday, even if you disable Location History, the search giant still tracks you every time you open Google Maps, get certain automatic weather updates, or search for things in your browser.

Thus Google had to rely on external signals as their primary ranking factor:

The reason that PageRank is interesting is that there are many cases where simple citation counting does not correspond to our common sense notion of importance. For example, if a web page has a link on the Yahoo home page, it may be just one link but it is a very important one. This page should be ranked higher than many pages with more links but from obscure places. PageRank is an attempt to see how good an approximation to "importance" can be obtained just from the link structure. ... The denition of PageRank above has another intuitive basis in random walks on graphs. The simplied version corresponds to the standing probability distribution of a random walk on the graph of the Web. Intuitively, this can be thought of as modeling the behavior of a "random surfer".

Google's reliance on links turned links into a commodity, which led to all sorts of fearmongering, manual penalties, nofollow and the Penguin update.

As Google collected more usage data those who overly focused on links often ended up scoring an own goal, creating sites which would not rank.

Google no longer invests heavily in fearmongering because it is no longer needed. Search is so complex most people can't figure it out.

Many SEOs have reduced their link building efforts as Google dialed up weighting on user engagement metrics, though it appears the tide may now be heading in the other direction. Some sites which had decent engagement metrics but little in the way of link building slid on the update late last month.

As much as Google desires relevancy in the short term, they also prefer a system complex enough to external onlookers that reverse engineering feels impossible. If they discourage investment in SEO they increase AdWords growth while gaining greater control over algorithmic relevancy.

Google will soon collect even more usage data by routing Chrome users through their DNS service: "Google isn't actually forcing Chrome users to only use Google's DNS service, and so it is not centralizing the data. Google is instead configuring Chrome to use DoH connections by default if a user's DNS service supports it."

If traffic is routed through Google that is akin to them hosting the page in terms of being able to track many aspects of user behavior. It is akin to AMP or YouTube in terms of being able to track users and normalize relative engagement metrics.

Once Google is hosting the end-to-end user experience they can create a near infinite number of ranking signals given their advancement in computing power: "We developed a new 54-qubit processor, named “Sycamore”, that is comprised of fast, high-fidelity quantum logic gates, in order to perform the benchmark testing. Our machine performed the target computation in 200 seconds, and from measurements in our experiment we determined that it would take the world’s fastest supercomputer 10,000 years to produce a similar output."

Relying on "one simple trick to..." sorts of approaches are frequently going to come up empty.

EMDs Kicked Once Again

I was one of the early promoters of exact match domains when the broader industry did not believe in them. I was also quick to mention when I felt the algorithms had moved in the other direction.

Google's mobile layout, which they are now testing on desktop computers as well, replaces green domain names with gray words which are easy to miss. And the favicon icons sort of make the organic results look like ads. Any boost a domain name like CreditCards.ext might have garnered in the past due to matching the keyword has certainly gone away with this new layout that further depreciates the impact of exact-match domain names.

At one point in time CreditCards.com was viewed as a consumer destination. It is now viewed ... below the fold.

If you have a memorable brand-oriented domain name the favicon can help offset the above impact somewhat, but matching keywords is becoming a much more precarious approach to sustaining rankings as the weight on brand awareness, user engagement & authority increase relative to the weight on anchor text.

Categories:

google

New Keyword Tool

Aaron Wall — Sat, 14 Sep 2019 03:06:45 -0700

Our keyword tool is updated periodically. We recently updated it once more.

For comparison sake, the old keyword tool looked like this

Whereas the new keyword tool looks like this

The upsides of the new keyword tool are:

fresher data from this year
more granular data on ad bids vs click prices
lists ad clickthrough rate
more granular estimates of Google AdWords advertiser ad bids
more emphasis on commercial oriented keywords

With the new columns of [ad spend] and [traffic value] here is how we estimate those.

paid search ad spend: search ad clicks * CPC
organic search traffic value: ad impressions * 0.5 * (100% - ad CTR) * CPC

The first of those two is rather self explanatory. The second is a bit more complex. It starts with the assumption that about half of all searches do not get any clicks, then it subtracts the paid clicks from the total remaining pool of clicks & multiplies that by the cost per click.

The new data also has some drawbacks:

Rather than listing search counts specifically it lists relative ranges like low, very high, etc.
Since it tends to tilt more toward keywords with ad impressions, it may not have coverage for some longer tail informational keywords.

For any keyword where there is insufficient coverage we re-query the old keyword database for data & merge it across. You will know if data came from the new database if the first column says something like low or high & the data came from the older database if there are specific search counts in the first column

For a limited time we are still allowing access to both keyword tools, though we anticipate removing access to the old keyword tool in the future once we have collected plenty of feedback on the new keyword tool. Please feel free to leave your feedback in the below comments.

One of the cool features of the new keyword tools worth highlighting further is the difference between estimated bid prices & estimated click prices. In the following screenshot you can see how Amazon is estimated as having a much higher bid price than actual click price, largely because due to low keyword relevancy entities other than the official brand being arbitraged by Google require much higher bids to appear on competing popular trademark terms.

Historically, this difference between bid price & click price was a big source of noise on lists of the most valuable keywords.

Recently some advertisers have started complaining about the "Google shakedown" from how many brand-driven searches are simply leaving the .com part off of a web address in Chrome & then being forced to pay Google for their own pre-existing brand equity.

When Google puts 4 paid ads ahead of the first organic result for your own brand name, you’re forced to pay up if you want to be found. It’s a shakedown. It’s ransom. But at least we can have fun with it. Search for Basecamp and you may see this attached ad. pic.twitter.com/c0oYaBuahL
— Jason Fried (@jasonfried) September 3, 2019

Categories:

seo tools

AMP'd Up for Recaptcha

Aaron Wall — Sun, 30 Jun 2019 14:47:54 -0700

Beyond search Google controls the leading distributed ad network, the leading mobile OS, the leading web browser, the leading email client, the leading web analytics platform, the leading free video hosting site.

They win a lot.

And they take winnings from one market & leverage them into manipulating adjacent markets.

Embrace. Extend. Extinguish.

Imagine taking a universal open standard that has zero problems with it and then stripping it down to it's most basic components and then prepending each element with your own acronym. Then spend years building and recreating what has existed for decades. That is @amphtml— Jon Henshaw (@henshaw) April 4, 2019

AMP is an utterly unnecessary invention designed to further shift power to Google while disenfranchising publishers. From the very start it had many issues with basic things like supporting JavaScript, double counting unique users (no reason to fix broken stats if they drive adoption!), not supporting third party ad networks, not showing publisher domain names, and just generally being a useless layer of sunk cost technical overhead that provides literally no real value.

Over time they have corrected some of these catastrophic deficiencies, but if it provided real value, they wouldn't have needed to force adoption with preferential placement in their search results. They force the bundling because AMP sucks.

Absurdity knows no bounds. Googlers suggest: "AMP isn’t another “channel” or “format” that’s somehow not the web. It’s not a SEO thing. It’s not a replacement for HTML. It’s a web component framework that can power your whole site. ... We, the AMP team, want AMP to become a natural choice for modern web development of content websites, and for you to choose AMP as framework because it genuinely makes you more productive."

Meanwhile some newspapers have about a dozen employees who work on re-formatting content for AMP:

The AMP development team now keeps track of whether AMP traffic drops suddenly, which might indicate pages are invalid, and it can react quickly.

All this adds expense, though. There are setup, development and maintenance costs associated with AMP, mostly in the form of time. After implementing AMP, the Guardian realized the project needed dedicated staff, so it created an 11-person team that works on AMP and other aspects of the site, drawing mostly from existing staff.

Feeeeeel the productivity!

Some content types (particularly user generated content) can be unpredictable & circuitous. For many years forums websites would use keywords embedded in the search referral to highlight relevant parts of the page. Keyword (not provided) largely destroyed that & then it became a competitive feature for AMP: "If the Featured Snippet links to an AMP article, Google will sometimes automatically scroll users to that section and highlight the answer in orange."

That would perhaps be a single area where AMP was more efficient than the alternative. But it is only so because Google destroyed the alternative by stripping keyword referrers from search queries.

The power dynamics of AMP are ugly:

"I see them as part of the effort to normalise the use of the AMP Carousel, which is an anti-competitive land-grab for the web by an organisation that seems to have an insatiable appetite for consuming the web, probably ultimately to it’s own detriment. ... This enables Google to continue to exist after the destination site (eg the New York Times) has been navigated to. Essentially it flips the parent-child relationship to be the other way around. ... As soon as a publisher blesses a piece of content by packaging it (they have to opt in to this, but see coercion below), they totally lose control of its distribution. ... I’m not that smart, so it’s surely possible to figure out other ways of making a preload possible without cutting off the content creator from the people consuming their content. ... The web is open and decentralised. We spend a lot of time valuing the first of these concepts, but almost none trying to defend the second. Google knows, perhaps better than anyone, how being in control of the user is the most monetisable position, and having the deepest pockets and the most powerful platform to do so, they have very successfully inserted themselves into my relationship with millions of other websites. ... In AMP, the support for paywalls is based on a recommendation that the premium content be included in the source of the page regardless of the user’s authorisation state. ... These policies demonstrate contempt for others’ right to freely operate their businesses.

After enough publishers adopted AMP Google was able to turn their mobile app's homepage into an interactive news feed below the search box. And inside that news feed Google gets to distribute MOAR ads while 0% of the revenue from those ads find its way to the publishers whose content is used to make up the feed.

Appropriate appropriation. :D

Each additional layer of technical cruft is another cost center. Things that sound appealing at first blush may not be:

The way you verify your identity to Let's Encrypt is the same as with other certificate authorities: you don't really. You place a file somewhere on your website, and they access that file over plain HTTP to verify that you own the website. The one attack that signed certificates are meant to prevent is a man-in-the-middle attack. But if someone is able to perform a man-in-the-middle attack against your website, then he can intercept the certificate verification, too. In other words, Let's Encrypt certificates don't stop the one thing they're supposed to stop. And, as always with the certificate authorities, a thousand murderous theocracies, advertising companies, and international spy organizations are allowed to impersonate you by design.

Anything that is easy to implement & widely marketed often has costs added to it in the future as the entity moves to monetize the service.

This is a private equity firm buying up multiple hosting control panels & then adjusting prices.

This is Google Maps drastically changing their API terms.

This is Facebook charging you for likes to build an audience, giving your competitors access to those likes as an addressable audience to advertise against, and then charging you once more to boost the reach of your posts.

This is Grubhub creating shadow websites on your behalf and charging you for every transaction created by the gravity of your brand.

Shivane believes GrubHub purchased her restaurant’s web domain to prevent her from building her own online presence. She also believes the company may have had a special interest in owning her name because she processes a high volume of orders. ... it appears GrubHub has set up several generic, templated pages that look like real restaurant websites but in fact link only to GrubHub. These pages also display phone numbers that GrubHub controls. The calls are forwarded to the restaurant, but the platform records each one and charges the restaurant a commission fee for every order

Settling for the easiest option drives a lack of differentiation, embeds additional risk & once the dominant player has enough marketshare they'll change the terms on you.

Small gains in short term margins for massive increases in fragility.

"Closed platforms increase the chunk size of competition & increase the cost of market entry, so people who have good ideas, it is a lot more expensive for their productivity to be monetized. They also don't like standardization ... it looks like rent seeking behaviors on top of friction" - Gabe Newell

The other big issue is platforms that run out of growth space in their core market may break integrations with adjacent service providers as each want to grow by eating the other's market.

Those who look at SaaS business models through the eyes of a seasoned investor will better understand how markets are likely to change:

"I’d argue that many of today’s anointed tech “disruptors” are doing little in the way of true disruption. ... When investors used to get excited about a SAAS company, they typically would be describing a hosted multi-tenant subscription-billed piece of software that was replacing a ‘legacy’ on-premise perpetual license solution in the same target market (i.e. ERP, HCM, CRM, etc.). Today, the terms SAAS and Cloud essentially describe the business models of every single public software company.

Most platform companies are initially required to operate at low margins in order to buy growth of their category & own their category. Then when they are valued on that, they quickly need to jump across to adjacent markets to grow into the valuation:

Twilio has no choice but to climb up the application stack. This is a company whose ‘disruption’ is essentially great API documentation and gangbuster SEO spend built on top of a highly commoditized telephony aggregation API. They have won by marketing to DevOps engineers. With all the hype around them, you’d think Twilio invented the telephony API, when in reality what they did was turn it into a product company. Nobody had thought of doing this let alone that this could turn into a $17 billion company because simply put the economics don’t work. And to be clear they still don’t. But Twilio’s genius CEO clearly gets this. If the market is going to value robocalls, emergency sms notifications, on-call pages, and carrier fee passed through related revenue growth in the same way it does ‘subscription’ revenue from Atlassian or ServiceNow, then take advantage of it while it lasts.

Large platforms offering temporary subsidies to ensure they dominate their categories & companies like SoftBank spraying capital across the markets is causing massive shifts in valuations:

I also think if you look closely at what is celebrated today as innovation you often find models built on hidden subsidies. ... I’d argue the very distributed nature of microservices architecture and API-first product companies means addressable market sizes and unit economics assumptions should be even more carefully scrutinized. ... How hard would it be to create an Alibaba today if someone like SoftBank was raining money into such a greenfield space? Excess capital would lead to destruction and likely subpar returns. If capital was the solution, the 1.5 trillion that went into telcos in late '90s wouldn’t have led to a massive bust. Would a Netflix be what it is today if a SoftBank was pouring billions into streaming content startups right as the experiment was starting? Obviously not. Scarcity of capital is another often underappreciated part of the disruption equation. Knowing resources are finite leads to more robust models. ... This convergence is starting to manifest itself in performance. Disney is up 30% over the last 12 months while Netflix is basically flat. This may not feel like a bubble sign to most investors, but from my standpoint, it’s a clear evidence of the fact that we are approaching a something has got to give moment for the way certain businesses are valued."

Circling back to Google's AMP, it has a cousin called Recaptcha.

Recaptcha is another AMP-like trojan horse:

According to tech statistics website Built With, more than 650,000 websites are already using reCaptcha v3; overall, there are at least 4.5 million websites use reCaptcha, including 25% of the top 10,000 sites. Google is also now testing an enterprise version of reCaptcha v3, where Google creates a customized reCaptcha for enterprises that are looking for more granular data about users’ risk levels to protect their site algorithms from malicious users and bots. ... According to two security researchers who’ve studied reCaptcha, one of the ways that Google determines whether you’re a malicious user or not is whether you already have a Google cookie installed on your browser. ... To make this risk-score system work accurately, website administrators are supposed to embed reCaptcha v3 code on all of the pages of their website, not just on forms or log-in pages.

About a month ago when logging into Bing Ads I saw recaptcha on the login page & couldn't believe they'd give Google control at that access point. I think they got rid of that, but lots of companies are perhaps shooting themselves in the foot through a combination of over-reliance on Google infrastructure AND sloppy implementation

Today when making a purchase on Fiverr, after converting, I got some of this action

Hmm. Maybe I will enable JavaScript and try again.

Oooops.

That is called snatching defeat from the jaws of victory.

My account is many years old. My payment type on record has been used for years. I have ordered from the particular seller about a dozen times over the years. And suddenly because my web browser had JavaScript turned off I was deemed a security risk of some sort for making an utterly ordinary transaction I have already completed about a dozen times.

On AMP JavaScript was the devil. And on desktop not JavaScript was the devil.

Pro tip: Ecommerce websites that see substandard conversion rates from using Recaptcha can boost their overall ecommerce revenue by buying more Google AdWords ads.

---

As more of the infrastructure stack is driven by AI software there is going to be a very real opportunity for many people to become deplatformed across the web on an utterly arbitrary basis. That tech companies like Facebook also want to create digital currencies on top of the leverage they already have only makes the proposition that much scarier.

If the tech platforms host copies of our sites, process the transactions & even create their own currencies, how will we know what level of value they are adding versus what they are extracting?

Who measures the measurer?

And when the economics turn negative, what will we do if we are hooked into an ecosystem we can't spend additional capital to get out of when things head south?

Categories:

google

The Fractured Web

Aaron Wall — Wed, 17 Apr 2019 11:09:18 -0700

Anyone can argue about the intent of a particular action & the outcome that is derived by it. But when the outcome is known, at some point the intent is inferred if the outcome is derived from a source of power & the outcome doesn't change.

Or, put another way, if a powerful entity (government, corporation, other organization) disliked an outcome which appeared to benefit them in the short term at great lasting cost to others, they could spend resources to adjust the system.

If they don't spend those resources (or, rather, spend them on lobbying rather than improving the ecosystem) then there is no desired change. The outcome is as desired. Change is unwanted.

Engagement is a toxic metric.Products which optimize for it become worse. People who optimize for it become less happy.It also seems to generate runaway feedback loops where most engagable people have a) worst individual experiences and then b) end up driving the product bus.— Patrick McKenzie (@patio11) April 9, 2019

News is a stock vs flow market where the flow of recent events drives most of the traffic to articles. News that is more than a couple days old is no longer news. A news site which stops publishing news stops becoming a habit & quickly loses relevancy. Algorithmically an abandoned archive of old news articles doesn't look much different than eHow, in spite of having a much higher cost structure.

According to SEMrush's traffic rank, ampproject.org gets more monthly visits than Yahoo.com.

That actually understates the prevalence of AMP because AMP is generally designed for mobile AND not all AMP-formatted content is displayed on ampproject.org.

Part of how AMP was able to get widespread adoption was because in the news vertical the organic search result set was displaced by an AMP block. If you were a news site either you were so differentiated that readers would scroll past the AMP block in the search results to look for you specifically, or you adopted AMP, or you were doomed.

Some news organizations like The Guardian have a team of about a dozen people reformatting their content to the duplicative & proprietary AMP format. That's wasteful, but necessary "In theory, adoption of AMP is voluntary. In reality, publishers that don’t want to see their search traffic evaporate have little choice. New data from publisher analytics firm Chartbeat shows just how much leverage Google has over publishers thanks to its dominant search engine."

It seems more than a bit backward that low margin publishers are doing duplicative work to distance themselves from their own readers while improving the profit margins of monopolies. But it is what it is. And that no doubt drew the ire of many publishers across the EU.

And now there are AMP Stories to eat up even more visual real estate.

If you spent a bunch of money to create a highly differentiated piece of content, why would you prefer that high spend flaghship content appear on a third party website rather than your own?

Google & Facebook have done such a fantastic job of eating the entire pie that some are celebrating Amazon as a prospective savior to the publishing industry. That view - IMHO - is rather suspect.

Where any of the tech monopolies dominate they cram down on partners. The New York Times acquired The Wirecutter in Q4 of 2016. In Q1 of 2017 Amazon adjusted their affiliate fee schedule.

Amazon generally treats consumers well, but they have been much harder on business partners with tough pricing negotiations, counterfeit protections, forced ad buying to have a high enough product rank to be able to rank organically, ad displacement of their organic search results below the fold (even for branded search queries), learning suppliers & cutting out the partners, private label products patterned after top sellers, in some cases running pop over ads for the private label products on product level pages where brands already spent money to drive traffic to the page, etc.

They've made things tougher for their partners in a way that mirrors the impact Facebook & Google have had on online publishers:

"Boyce’s experience on Amazon largely echoed what happens in the offline world: competitors entered the market, pushing down prices and making it harder to make a profit. So Boyce adapted. He stopped selling basketball hoops and developed his own line of foosball tables, air hockey tables, bocce ball sets and exercise equipment. The best way to make a decent profit on Amazon was to sell something no one else had and create your own brand. ... Amazon also started selling bocce ball sets that cost $15 less than Boyce’s. He says his products are higher quality, but Amazon gives prominent page space to its generic version and wins the cost-conscious shopper."

Google claims they have no idea how content publishers are with the trade off between themselves & the search engine, but every quarter Alphabet publish the share of ad spend occurring on owned & operated sites versus the share spent across the broader publisher network. And in almost every quarter for over a decade straight that ratio has grown worse for publishers.

When Google tells industry about how much $ it funnels to rest of ecosystem, just show them this chart. It's good to be the "revenue regulator" (note: G went public in 2004). pic.twitter.com/HCbCNgbzKc— Jason Kint (@jason_kint) February 5, 2019

The aggregate numbers for news publishers are worse than shown above as Google is ramping up ads in video games quite hard. They've partnered with Unity & promptly took away the ability to block ads from appearing in video games using googleadsenseformobileapps.com exclusion (hello flat thumb misclicks, my name is budget & I am gone!)

They will also track video game player behavior & alter game play to maximize revenues based on machine learning tied to surveillance of the user's account: "We’re bringing a new approach to monetization that combines ads and in-app purchases in one automated solution. Available today, new smart segmentation features in Google AdMob use machine learning to segment your players based on their likelihood to spend on in-app purchases. Ad units with smart segmentation will show ads only to users who are predicted not to spend on in-app purchases. Players who are predicted to spend will see no ads, and can simply continue playing."

And how does the growth of ampproject.org square against the following wisdom?

If you do use a CDN, I'd recommend using a domain name of your own (eg, https://t.co/fWMc6CFPZ0), so you can move to other CDNs if you feel the need to over time, without having to do any redirects.— John (@JohnMu) April 15, 2019

Literally only yesterday did Google begin supporting instant loading of self-hosted AMP pages.

China has a different set of tech leaders than the United States. Baidu, Alibaba, Tencent (BAT) instead of Facebook, Amazon, Apple, Netflix, Google (FANG). China tech companies may have won their domestic markets in part based on superior technology or better knowledge of the local culture, though those same companies have largely went nowhere fast in most foreign markets. A big part of winning was governmental assistance in putting a foot on the scales.

Part of the US-China trade war is about who controls the virtual "seas" upon which value flows:

it can easily be argued that the last 60 years were above all the era of the container-ship (with container-ships getting ever bigger). But will the coming decades still be the age of the container-ship? Possibly not, for the simple reason that things that have value increasingly no longer travel by ship, but instead by fiberoptic cables! ... you could almost argue that ZTE and Huawei have been the “East India Company” of the current imperial cycle. Unsurprisingly, it is these very companies, charged with laying out the “new roads” along which “tomorrow’s value” will flow, that find themselves at the center of the US backlash. ... if the symbol of British domination was the steamship, and the symbol of American strength was the Boeing 747, it seems increasingly clear that the question of the future will be whether tomorrow’s telecom switches and routers are produced by Huawei or Cisco. ... US attempts to take down Huawei and ZTE can be seen as the existing empire’s attempt to prevent the ascent of a new imperial power. With this in mind, I could go a step further and suggest that perhaps the Huawei crisis is this century’s version of Suez crisis. No wonder markets have been falling ever since the arrest of the Huawei CFO. In time, the Suez Crisis was brought to a halt by US threats to destroy the value of sterling. Could we now witness the same for the US dollar?

China maintains Huawei is an employee-owned company. But that proposition is suspect. Broadly stealing technology is vital to the growth of the Chinese economy & they have no incentive to stop unless their leading companies pay a direct cost. Meanwhile, China is investigating Ericsson over licensing technology.

Amazon will soon discontinue selling physical retail products in China: "Amazon shoppers in China will no longer be able to buy goods from third-party merchants in the country, but they still will be able to order from the United States, Britain, Germany and Japan via the firm’s global store. Amazon expects to close fulfillment centers and wind down support for domestic-selling merchants in China in the next 90 days."

India has taken notice of the success of Chinese tech companies & thus began to promote "national champion" company policies. That, in turn, has also meant some of the Chinese-styled laws requiring localized data, antitrust inquiries, foreign ownership restrictions, requirements for platforms to not sell their own goods, promoting limits on data encryption, etc.

The secretary of India’s Telecommunications Department, Aruna Sundararajan, last week told a gathering of Indian startups in a closed-door meeting in the tech hub of Bangalore that the government will introduce a “national champion” policy “very soon” to encourage the rise of Indian companies, according to a person familiar with the matter. She said Indian policy makers had noted the success of China’s internet giants, Alibaba Group Holding Ltd. and Tencent Holdings Ltd. ... Tensions began rising last year, when New Delhi decided to create a clearer set of rules for e-commerce and convened a group of local players to solicit suggestions. Amazon and Flipkart, even though they make up more than half the market, weren’t invited, according to people familiar with the matter.

Amazon vowed to invest $5 billion in India & they have done some remarkable work on logistics there. Walmart acquired Flipkart for $16 billion.

Other emerging markets also have many local ecommerce leaders like Jumia, MercadoLibre, OLX, Gumtree, Takealot, Konga, Kilimall, BidOrBuy, Tokopedia, Bukalapak, Shoppee, Lazada. If you live in the US you may have never heard of *any* of those companies. And if you live in an emerging market you may have never interacted with Amazon or eBay.

It makes sense that ecommerce leadership would be more localized since it requires moving things in the physical economy, dealing with local currencies, managing inventory, shipping goods, etc. whereas information flows are just bits floating on a fiber optic cable.

If the Internet is primarily seen as a communications platform it is easy for people in some emerging markets to think Facebook is the Internet. Free communication with friends and family members is a compelling offer & as the cost of data drops web usage increases.

At the same time, the web is incredibly deflationary. Every free form of entertainment which consumes time is time that is not spent consuming something else.

Add the technological disruption to the wealth polarization that happened in the wake of the great recession, then combine that with algorithms that promote extremist views & it is clearly causing increasing conflict.

If you are a parent and you think you child has no shot at a brighter future than your own life it is easy to be full of rage.

Empathy can radicalize otherwise normal people by giving them a more polarized view of the world:

Starting around 2000, the line starts to slide. More students say it's not their problem to help people in trouble, not their job to see the world from someone else's perspective. By 2009, on all the standard measures, Konrath found, young people on average measure 40 percent less empathetic than my own generation ... The new rule for empathy seems to be: reserve it, not for your "enemies," but for the people you believe are hurt, or you have decided need it the most. Empathy, but just for your own team. And empathizing with the other team? That's practically a taboo.

A complete lack of empathy could allow a psychopath to commit extreme crimes while feeling no guilt, shame or remorse. Extreme empathy can have the same sort of outcome:

"Sometimes we commit atrocities not out of a failure of empathy but rather as a direct consequence of successful, even overly successful, empathy. ... They emphasized that students would learn both sides, and the atrocities committed by one side or the other were always put into context. Students learned this curriculum, but follow-up studies showed that this new generation was more polarized than the one before. ... [Empathy] can be good when it leads to good action, but it can have downsides. For example, if you want the victims to say 'thank you.' You may even want to keep the people you help in that position of inferior victim because it can sustain your feeling of being a hero." - Fritz Breithaupt

News feeds will be read. Villages will be razed. Lynch mobs will become commonplace.

Many people will end up murdered by algorithmically generated empathy.

As technology increases absentee ownership & financial leverage, a society led by morally agnostic algorithms is not going to become more egalitarian.

The more I think about and discuss it, the more I think WhatsApp is simultaneously the future of Facebook, and the most potentially dangerous digital tool yet created. We haven't even begun to see the real impact yet of ubiquitous, unfettered and un-moderatable human telepathy.— Antonio García Martínez (@antoniogm) April 15, 2019

When politicians throw fuel on the fire it only gets worse:

It’s particularly odd that the government is demanding “accountability and responsibility” from a phone app when some ruling party politicians are busy spreading divisive fake news. How can the government ask WhatsApp to control mobs when those convicted of lynching Muslims have been greeted, garlanded and fed sweets by some of the most progressive and cosmopolitan members of Modi’s council of ministers?

Mark Zuckerburg won't get caught downstream from platform blowback as he spends $20 million a year on his security.

The web is a mirror. Engagement-based algorithms reinforcing our perceptions & identities.

And every important story has at least 2 sides!

The Rohingya asylum seekers are victims of their own violent Jihadist leadership that formed a militia to kill Buddhists and Hindus. Hindus are being massacred, where’s the outrage for them!? https://t.co/P3m6w4B1Po— Imam Tawhidi (@Imamofpeace) May 23, 2018

Some may "learn" vaccines don't work. Others may learn the vaccines their own children took did not work, as it failed to protect them from the antivax content spread by Facebook & Google, absorbed by people spreading measles & Medieval diseases.

Passion drives engagement, which drives algorithmic distribution: "There’s an asymmetry of passion at work. Which is to say, there’s very little counter-content to surface because it simply doesn’t occur to regular people (or, in this case, actual medical experts) that there’s a need to produce counter-content."

As the costs of "free" become harder to hide, social media companies which currently sell emerging markets as their next big growth area will end up having embedded regulatory compliance costs which will end up exceeding any sort of prospective revenue they could hope to generate.

The Pinterest S1 shows almost all their growth is in emerging markets, yet almost all their revenue is inside the United States.

As governments around the world see the real-world cost

Keyword Not Provided, But it Just Clicks

Aaron Wall — Tue, 09 Apr 2019 08:09:28 -0700

When SEO Was Easy

When I got started on the web over 15 years ago I created an overly broad & shallow website that had little chance of making money because it was utterly undifferentiated and crappy. In spite of my best (worst?) efforts while being a complete newbie, sometimes I would go to the mailbox and see a check for a couple hundred or a couple thousand dollars come in. My old roommate & I went to Coachella & when the trip was over I returned to a bunch of mail to catch up on & realized I had made way more while not working than what I spent on that trip.

What was the secret to a total newbie making decent income by accident?

Horrible spelling.

Back then search engines were not as sophisticated with their spelling correction features & I was one of 3 or 4 people in the search index that misspelled the name of an online casino the same way many searchers did.

The high minded excuse for why I did not scale that would be claiming I knew it was a temporary trick that was somehow beneath me. The more accurate reason would be thinking in part it was a lucky fluke rather than thinking in systems. If I were clever at the time I would have created the misspeller's guide to online gambling, though I think I was just so excited to make anything from the web that I perhaps lacked the ambition & foresight to scale things back then.

In the decade that followed I had a number of other lucky breaks like that. One time one of the original internet bubble companies that managed to stay around put up a sitewide footer link targeting the concept that one of my sites made decent money from. This was just before the great recession, before Panda existed. The concept they targeted had 3 or 4 ways to describe it. 2 of them were very profitable & if they targeted either of the most profitable versions with that page the targeting would have sort of carried over to both. They would have outranked me if they targeted the correct version, but they didn't so their mistargeting was a huge win for me.

Search Gets Complex

Search today is much more complex. In the years since those easy-n-cheesy wins, Google has rolled out many updates which aim to feature sought after destination sites while diminishing the sites which rely one "one simple trick" to rank.

Arguably the quality of the search results has improved significantly as search has become more powerful, more feature rich & has layered in more relevancy signals.

Many quality small web publishers have went away due to some combination of increased competition, algorithmic shifts & uncertainty, and reduced monetization as more ad spend was redirected toward Google & Facebook. But the impact as felt by any given publisher is not the impact as felt by the ecosystem as a whole. Many terrible websites have also went away, while some formerly obscure though higher-quality sites rose to prominence.

There was the Vince update in 2009, which boosted the rankings of many branded websites.

Then in 2011 there was Panda as an extension of Vince, which tanked the rankings of many sites that published hundreds of thousands or millions of thin content pages while boosting the rankings of trusted branded destinations.

Then there was Penguin, which was a penalty that hit many websites which had heavily manipulated or otherwise aggressive appearing link profiles. Google felt there was a lot of noise in the link graph, which was their justification for the Penguin.

There were updates which lowered the rankings of many exact match domains. And then increased ad load in the search results along with the other above ranking shifts further lowered the ability to rank keyword-driven domain names. If your domain is generically descriptive then there is a limit to how differentiated & memorable you can make it if you are targeting the core market the keywords are aligned with.

There is a reason eBay is more popular than auction.com, Google is more popular than search.com, Yahoo is more popular than portal.com & Amazon is more popular than a store.com or a shop.com. When that winner take most impact of many online markets is coupled with the move away from using classic relevancy signals the economics shift to where is makes a lot more sense to carry the heavy overhead of establishing a strong brand.

Branded and navigational search queries could be used in the relevancy algorithm stack to confirm the quality of a site & verify (or dispute) the veracity of other signals.

Historically relevant algo shortcuts become less appealing as they become less relevant to the current ecosystem & even less aligned with the future trends of the market. Add in negative incentives for pushing on a string (penalties on top of wasting the capital outlay) and a more holistic approach certainly makes sense.

Modeling Web Users & Modeling Language

PageRank was an attempt to model the random surfer.

When Google is pervasively monitoring most users across the web they can shift to directly measuring their behaviors instead of using indirect signals.

Years ago Bill Slawski wrote about the long click in which he opened by quoting Steven Levy's In the Plex: How Google Thinks, Works, and Shapes our Lives

"On the most basic level, Google could see how satisfied users were. To paraphrase Tolstoy, happy users were all the same. The best sign of their happiness was the "Long Click" — This occurred when someone went to a search result, ideally the top one, and did not return. That meant Google has successfully fulfilled the query."

Of course, there's a patent for that. In Modifying search result ranking based on implicit user feedback they state:

user reactions to particular search results or search result lists may be gauged, so that results on which users often click will receive a higher ranking. The general assumption under such an approach is that searching users are often the best judges of relevance, so that if they select a particular search result, it is likely to be relevant, or at least more relevant than the presented alternatives.

If you are a known brand you are more likely to get clicked on than a random unknown entity in the same market.

And if you are something people are specifically seeking out, they are likely to stay on your website for an extended period of time.

One aspect of the subject matter described in this specification can be embodied in a computer-implemented method that includes determining a measure of relevance for a document result within a context of a search query for which the document result is returned, the determining being based on a first number in relation to a second number, the first number corresponding to longer views of the document result, and the second number corresponding to at least shorter views of the document result; and outputting the measure of relevance to a ranking engine for ranking of search results, including the document result, for a new search corresponding to the search query. The first number can include a number of the longer views of the document result, the second number can include a total number of views of the document result, and the determining can include dividing the number of longer views by the total number of views.

Attempts to manipulate such data may not work.

safeguards against spammers (users who generate fraudulent clicks in an attempt to boost certain search results) can be taken to help ensure that the user selection data is meaningful, even when very little data is available for a given (rare) query. These safeguards can include employing a user model that describes how a user should behave over time, and if a user doesn't conform to this model, their click data can be disregarded. The safeguards can be designed to accomplish two main objectives: (1) ensure democracy in the votes (e.g., one single vote per cookie and/or IP for a given query-URL pair), and (2) entirely remove the information coming from cookies or IP addresses that do not look natural in their browsing behavior (e.g., abnormal distribution of click positions, click durations, clicks_per_minute/hour/day, etc.). Suspicious clicks can be removed, and the click signals for queries that appear to be spmed need not be used (e.g., queries for which the clicks feature a distribution of user agents, cookie ages, etc. that do not look normal).

And just like Google can make a matrix of documents & queries, they could also choose to put more weight on search accounts associated with topical expert users based on their historical click patterns.

Moreover, the weighting can be adjusted based on the determined type of the user both in terms of how click duration is translated into good clicks versus not-so-good clicks, and in terms of how much weight to give to the good clicks from a particular user group versus another user group. Some user's implicit feedback may be more valuable than other users due to the details of a user's review process. For example, a user that almost always clicks on the highest ranked result can have his good clicks assigned lower weights than a user who more often clicks results lower in the ranking first (since the second user is likely more discriminating in his assessment of what constitutes a good result). In addition, a user can be classified based on his or her query stream. Users that issue many queries on (or related to) a given topic T (e.g., queries related to law) can be presumed to have a high degree of expertise with respect to the given topic T, and their click data can be weighted accordingly for other queries by them on (or related to) the given topic T.

Google was using click data to drive their search rankings as far back as 2009. David Naylor was perhaps the first person who publicly spotted this. Google was ranking Australian websites for [tennis court hire] in the UK & Ireland, in part because that is where most of the click signal came from. That phrase was most widely searched for in Australia. In the years since Google has done a better job of geographically isolating clicks to prevent things like the problem David Naylor noticed, where almost all search results in one geographic region came from a different country.

Whenever SEOs mention using click data to search engineers, the search engineers quickly respond about how they might consider any signal but clicks would be a noisy signal. But if a signal has noise an engineer would work around the noise by finding ways to filter the noise out or combine multiple signals. To this day Google states they are still working to filter noise from the link graph: "We continued to protect the value of authoritative and relevant links as an important ranking signal for Search."

The site with millions of inbound links, few intentional visits & those who do visit quickly click the back button (due to a heavy ad load, poor user experience, low quality content, shallow content, outdated content, or some other bait-n-switch approach)...that's an outlier. Preventing those sorts of sites from ranking well would be another way of protecting the value of authoritative & relevant links.

Best Practices Vary Across Time & By Market + Category

Along the way, concurrent with the above sorts of updates, Google also improved their spelling auto-correct features, auto-completed search queries for many years through a featured called Google Instant (though they later undid forced query auto-completion while retaining automated search suggestions), and then they rolled out a few other algorithms that further allowed them to model language & user behavior.

Today it would be much harder to get paid above median wages explicitly for sucking at basic spelling or scaling some other individual shortcut to the moon, like pouring millions of low quality articles into a (formerly!) trusted domain.

Nearly a decade after Panda, eHow's rankings still haven't recovered.

Back when I got started with SEO the phrase Indian SEO company was associated with cut-rate work where people were buying exclusively based on price. Sort of like a "I got a $500 budget for link building, but can not under any circumstance invest more than $5 in any individual link." Part of how my wife met me was she hired a hack SEO from San Diego who outsourced all the work to India and marked the price up about 100-fold while claiming it was all done in the United States. He created reciprocal links pages that got her site penalized & it didn't rank until after she took her reciprocal links page down.

With that sort of behavior widespread (hack US firm teaching people working in an emerging market poor practices), it likely meant many SEO "best practices" which were learned in an emerging market (particularly where the web was also underdeveloped) would be more inclined to being spammy. Considering how far ahead many Western markets were on the early Internet & how India has so many languages & how most web usage in India is based on mobile devices where it is hard for users to create links, it only makes sense that Google would want to place more weight on end user data in such a market.

If you set your computer location to India Bing's search box lists 9 different languages to choose from.

The above is not to state anything derogatory about any emerging market, but rather that various signals are stronger in some markets than others. And competition is stronger in some markets than others.

Search engines can only rank what exists.

"In a lot of Eastern European - but not just Eastern European markets - I think it is an issue for the majority of the [bream? muffled] countries, for the Arabic-speaking world, there just isn't enough content as compared to the percentage of the Internet population that those regions represent. I don't have up to date data, I know that a couple years ago we looked at Arabic for example and then the disparity was enormous. so if I'm not mistaken the Arabic speaking population of the world is maybe 5 to 6%, maybe more, correct me if I am wrong. But very definitely the amount of Arabic content in our index is several orders below that. So that means we do not have enough Arabic content to give to our Arabic users even if we wanted to. And you can exploit that amazingly easily and if you create a bit of content in Arabic, whatever it looks like we're gonna go you know we don't have anything else to serve this and it ends up being horrible. and people will say you know this works. I keyword stuffed the hell out of this page, bought some links, and there it is number one. There is nothing else to show, so yeah you're number one. the moment somebody actually goes out and creates high quality content that's there for the long haul, you'll be out and that there will be one." - Andrey Lipattsev – Search Quality Senior Strategist at Google Ireland, on Mar 23, 2016

Impacting the Economics of Publishing

Now search engines can certainly influence the economics of various types of media. At one point some otherwise credible media outlets were pitching the Demand Media IPO narrative that Demand Media was the publisher of the future & what other media outlets will look like. Years later, after heavily squeezing on the partner network & promoting programmatic advertising that reduces CPMs by the day Google is funding partnerships with multiple news publishers like McClatchy & Gatehouse to try to revive the news dead zones even Facebook is struggling with.

"Facebook Inc. has been looking to boost its local-news offerings since a 2017 survey showed most of its users were clamoring for more. It has run into a problem: There simply isn’t enough local news in vast swaths of the country. ... more than one in five newspapers have closed in the past decade and a half, leaving half the counties in the nation with just one newspaper, and 200 counties with no newspaper at all."

As mainstream newspapers continue laying off journalists, Facebook's news efforts are likely to continue failing unless they include direct economic incentives, as Google's programmatic ad push broke the banner ad:

"Thanks to the convoluted machinery of Internet advertising, the advertising world went from being about content publishers and advertising context—The Times unilaterally declaring, via its ‘rate card’, that ads in the Times Style section cost $30 per thousand impressions—to the users themselves and the data that targets them—Zappo’s saying it wants to show this specific shoe ad to this specific user (or type of user), regardless of publisher context. Flipping the script from a historically publisher-controlled mediascape to an advertiser (and advertiser intermediary) controlled one was really Google’s doing. Facebook merely rode the now-cresting wave, borrowing outside media’s content via its own users’ sharing, while undermining media’s ability to monetize via Facebook’s own user-data-centric advertising machinery. Conventional media lost both distribution and monetization at once, a mortal blow."

Google is offering news publishers audience development & business development tools.

Heavy Investment in Emerging Markets Quickly Evolves the Markets

As the web grows rapidly in India, they'll have a thousand flowers bloom. In 5 years the competition in India & other emerging markets will be much tougher as those markets continue to grow rapidly. Media is much cheaper to produce in India than it is in the United States. Labor costs are lower & they never had the economic albatross that is the ACA adversely impact their economy. At some point the level of investment & increased competition will mean early techniques stop having as much efficacy. Chinese companies are aggressively investing in India.

“If you break India into a pyramid, the top 100 million (urban) consumers who think and behave more like Americans are well-served,” says Amit Jangir, who leads India investments at 01VC, a Chinese venture capital firm based in Shanghai. The early stage venture firm has invested in micro-lending firms FlashCash and SmartCoin based in India. The new target is the next 200 million to 600 million consumers, who do not have a go-to entertainment, payment or ecommerce platform yet— and there is gonna be a unicorn in each of these verticals, says Jangir, adding that it will be not be as easy for a player to win this market considering the diversity and low ticket sizes.

RankBrain

RankBrain appears to be based on using user clickpaths on head keywords to help ble

How The Internet Happened: From Netscape to the iPhone

Aaron Wall — Sun, 07 Apr 2019 20:13:01 -0700

Brian McCullough, who runs Internet History Podcast, also wrote a book named How The Internet Happened: From Netscape to the iPhone which did a fantastic job of capturing the ethos of the early web and telling the backstory of so many people & projects behind it's evolution.

I think the quote which best the magic of the early web is

Jim Clark came from the world of machines and hardware, where development schedules were measured in years—even decades—and where “doing a startup” meant factories, manufacturing, inventory, shipping schedules and the like. But the Mosaic team had stumbled upon something simpler. They had discovered that you could dream up a product, code it, release it to the ether and change the world overnight. Thanks to the Internet, users could download your product, give you feedback on it, and you could release an update, all in the same day. In the web world, development schedules could be measured in weeks.

The part I bolded in the above quote from the book really captures the magic of the Internet & what pulled so many people toward the early web.

The current web - dominated by never-ending feeds & a variety of closed silos - is a big shift from the early days of web comics & other underground cool stuff people created & shared because they thought it was neat.

Many established players missed the actual direction of the web by trying to create something more akin to the web of today before the infrastructure could support it. Many of the "big things" driving web adoption relied heavily on chance luck - combined with a lot of hard work & a willingness to be responsive to feedback & data.

Even when Marc Andreessen moved to the valley he thought he was late and he had "missed the whole thing," but he saw the relentless growth of the web & decided making another web browser was the play that made sense at the time.
Tim Berners-Lee was dismayed when Andreessen's web browser enabled embedded image support in web documents.
Early Amazon review features were originally for editorial content from Amazon itself. Bezos originally wanted to launch a broad-based Amazon like it is today, but realized it would be too capital intensive & focused on books off the start so he could sell a known commodity with a long tail. Amazon was initially built off leveraging 2 book distributors ( Ingram and Baker & Taylor) & R. R. Bowker's Books In Print catalog. They also did clever hacks to meet minimum order requirements like ordering out of stock books as part of their order, so they could only order what customers had purchased.
eBay began as an /aw/ subfolder on the eBay domain name which was hosted on a residential internet connection. Pierre Omidyar coded the auction service over labor day weekend in 1995. The domain had other sections focused on topics like ebola. It was switched from AuctionWeb to a stand alone site only after the ISP started charging for a business line. It had no formal Paypal integration or anything like that, rather when listings started to charge a commission, merchants would mail physical checks in to pay for the platform share of their sales. Beanie Babies also helped skyrocket platform usage.
The reason AOL carpet bombed the United States with CDs - at their peak half of all CDs produced were AOL CDs - was their initial response rate was around 10%, a crazy number for untargeted direct mail.
Priceline was lucky to have survived the bubble as their idea was to spread broadly across other categories beyond travel & they were losing about $30 per airline ticket sold.
The broader web bubble left behind valuable infrastructure like unused fiber to fuel continued growth long after the bubble popped. The dot com bubble was possible in part because there was a secular bull market in bonds stemming back to the early 1980s & falling debt service payments increased financial leverage and company valuations.
TED members hissed at Bill Gross when he unveiled GoTo.com, which ranked "search" results based on advertiser bids.
Excite turned down offering the Google founders $1.6 million for the PageRank technology in part because Larry Page insisted to Excite CEO George Bell ‘If we come to work for Excite, you need to rip out all the Excite technology and replace it with [our] search.’ And, ultimately, that’s—in my recollection—where the deal fell apart.”
Steve Jobs initially disliked the multi-touch technology that mobile would rely on, one of the early iPhone prototypes had the iPod clickwheel, and Apple was against offering an app store in any form. Steve Jobs so loathed his interactions with the record labels that he did not want to build a phone & first licensed iTunes to Motorola, where they made the horrible ROKR phone. He only ended up building a phone after Cingular / AT&T begged him to.
Wikipedia was originally launched as a back up feeder site that was to feed into Nupedia.
Even after Facebook had strong traction, Marc Zuckerberg kept working on other projects like a file sharing service. Facebook's news feed was publicly hated based on the complaints, but it almost instantly led to a doubling of usage of the site so they never dumped it. After spreading from college to college Facebook struggled to expand ad other businesses & opening registration up to all was a hail mary move to see if it would rekindle growth instead of selling to Yahoo! for a billion dollars.

The book offers a lot of color to many important web related companies.

And many companies which were only briefly mentioned also ran into the same sort of lucky breaks the above companies did. Paypal was heavily reliant on eBay for initial distribution, but even that was something they initially tried to block until it became so obvious they stopped fighting it:

“At some point I sort of quit trying to stop the EBay users and mostly focused on figuring out how to not lose money,” Levchin recalls. ... In the late 2000s, almost a decade after it first went public, PayPal was drifting toward obsolescence and consistently alienating the small businesses that paid it to handle their online checkout. Much of the company’s code was being written offshore to cut costs, and the best programmers and designers had fled the company. ... PayPal’s conversion rate is lights-out: Eighty-nine percent of the time a customer gets to its checkout page, he makes the purchase. For other online credit and debit card transactions, that number sits at about 50 percent.

Here is a podcast interview of Brian McCullough by Chris Dixon.

How The Internet Happened: From Netscape to the iPhone is a great book well worth a read for anyone interested in the web.

Categories:

book reviews

Elite Las Vegas SEO Services

John White — Wed, 18 Oct 2017 04:27:10 -0700

Watch video on YouTube here: https://youtu.be/pe34_VlrQ2k
via www.elitelasvegasseo.com

Elite Las Vegas SEO Services

John White — Wed, 18 Oct 2017 04:16:40 -0700

Watch video on YouTube here: https://youtu.be/pe34_VlrQ2k
via www.youtube.com/ElitelasvegasseoTeam

Elite Las Vegas SEO Services https://youtu.be/pe34_VlrQ2k

Wed, 18 Oct 2017 04:14:24 -0700

Elite Las Vegas SEO Services
https://youtu.be/pe34_VlrQ2k

Do One Thing Everyday

Thu, 18 May 2017 13:21:19 -0700

The following post Do One Thing Everyday Find more on: Elite Las Vegas Marketing Company

Do One Thing Everyday That Scares You.

Las Vegas SEO Firm
702-530-9144
Online marketing for businesses of all shapes and sizes.

Do One Thing Everyday

John White — Thu, 18 May 2017 12:29:19 -0700

The following post Do One Thing Everyday Find more on: Elite Las Vegas Marketing Company

Do One Thing Everyday That Scares You.

Las Vegas SEO Firm
702-530-9144
Online marketing for businesses of all shapes and sizes.

Do One Thing Everyday

John White — Thu, 18 May 2017 12:27:15 -0700

The following post Do One Thing Everyday Find more on: Elite Las Vegas Marketing Company

Do One Thing Everyday That Scares You.

Las Vegas SEO Firm
702-530-9144
Online marketing for businesses of all shapes and sizes.

Risk it All

John White — Tue, 02 May 2017 12:32:27 -0700

The article Risk it All is available on Elite SEO

If you are not willing to risk it all, you will have to settle for the ordinary.

Las Vegas SEO Company
702.530.9144

Risk it All

Tue, 02 May 2017 12:29:13 -0700

The article Risk it All is available on Elite SEO

If you are not willing to risk it all, you will have to settle for the ordinary.

Las Vegas SEO Company
702.530.9144

Risk it All

John White — Tue, 02 May 2017 12:29:04 -0700

The article Risk it All is available on Elite SEO

If you are not willing to risk it all, you will have to settle for the ordinary.

Las Vegas SEO Company
702.530.9144

Realization of Tomorrow

John White — Tue, 25 Apr 2017 12:42:16 -0700

The following blog post Realization of Tomorrow See more on: http://elitelasvegasseo.com/

The only limit to our realization of tomorrow will be our doubts of today

SEO Las Vegas
Business #: +1.702.530.9144

Entrepreneurship and Success Quotes