This year’s TechSEO Boost, an event dedicated to technical SEO and hosted by Catalyst, took place on November 29 in Boston.
Billed as the conference “for developers and advanced SEO specialists,” TechSEO Boost built on the success of the inaugural event in 2017 with a day of enlightening, challenging talks from the sharpest minds in the industry.
Some topics permeated the discourse throughout the day and in particular, machine learning was a recurring theme.
As is the nature of the TechSEO Boost conference, the sessions aimed to go beyond the hype to define what precisely machine learning means for SEO, both today and in future.
The below is a recap of the excellent talk from Britney Muller, Senior SEO Scientist at Moz, entitled (fittingly enough) “Machine Learning for SEOs.”
What is machine learning? A quick recap.
The session opened with a brief primer on the key terms and concepts that fit under the umbrella of “machine learning.”
Muller used the definition in the image below to capture the sense of machine learning as “a subset of AI (Artificial Intelligence) that combines statistics and programming to give computers the ability to “learn” without explicitly being programmed.”
That core idea of “learning” from new stimuli is an important one to grasp as we consider how machine learning can be applied to daily SEO tasks.
Machine learning excels at identifying patterns in huge quantities of data. As such, some of the common examples of machine learning applications today include:
- Recommender systems (Netflix, Spotify)
- Ridesharing apps (Uber, Lyft)
- Digital Assistants (Amazon Alexa, Apple Siri, Google Assistant)
This very ubiquity can make it a challenging concept to grasp, however. In fact, Eric Schmidt at Google has gone so far as to say, “The core thing Google is working on is basically machine learning.”
It is helpful to break this down into the steps that comprise a typical machine learning project, in order to see how we might apply this to everyday SEO tasks.
The machine learning process
The image below represents the machine learning process Muller shared at TechSEO Boost:
It is important to bear in mind that some of the training data should be reserved for testing at a later point in the process.
Where possible, this data should also be labelled clearly to help the machine learning algorithm identify classifications and categories within a noisy data set.
It is for precisely this reason that Google asks us to label images to verify our identity:
This demonstrates our human ability to pick out objects in cluttered contexts, but it has the added benefit of providing Google with higher quality image data.
The pitfalls of an unsupervised approach to machine learning, and a training data set that is open to interpretation, were laid bare just last week.
Google’s ‘Smart Compose’ feature within Gmail has demonstrated gender bias by preferring certain pronouns when predicting what a user might want to say.
As reported in Reuters, “Gmail product manager Paul Lambert said a company research scientist discovered the problem in January when he typed “I am meeting an investor next week,” and Smart Compose suggested a possible follow-up question: “Do you want to meet him?” instead of “her.”
The challenge here is not restricted to projects on such a scale. Marketers who want to get their hands dirty must be aware of the limitations of machine learning, as well as its exciting possibilities.
Muller added that people tend to overfit their data, which reduces the accuracy and flexibility of the model they are using. This (very common) phenomenon occurs when a model corresponds very closely with one specific data set, reducing its applicability to new scenarios.
The ability to scale effectively is what gives machine learning its appeal, so overfitting is something to be avoided with care. There is a good primer to this topic here and it is also explained very well through this image:
So, how exactly can this subset of AI be used to improve SEO performance?
How you can use machine learning for SEO
As is the case with all hype-friendly technologies, businesses are keen to get involved with machine learning. However, the point is not to “use machine learning” through fear of being left behind, but rather to find the best uses of machine learning for each business.
Britney Muller shared some examples from her role at Moz during her session at TechSEO Boost.
The first was an approach to automated meta description generation using the Algorithmia Advanced Content Summarizer, which was then compared to Google’s approach to automated descriptions pulled directly from the landing page.
Meta descriptions remain an important asset when trying to encourage a positive click-through rate, but a lot of time is spent crafting these snippets. An automated alternative that can interpret the meaning of landing pages and create clickable summaries for display in the SERPs would be very useful.
Muller shared some examples, such as the image above, to demonstrate the comparison between the two approaches. The machine learning approach is not perfect and may require some tweaking, but it does an excellent job of conveying the page’s intent when compared to Google’s selection.
The team at Moz has since built this into Google Sheets:
Although this is not a product other businesses can access right now, an alternative way of achieving automated meta descriptions has been shared by Paul Shapiro (the TechSEO Boost host) via Github here.
Automated image optimization
Another fascinating use of machine learning for SEO is the automation of image optimization. Britney Muller showed how, in under 20 minutes, it is possible to train an algorithm to distinguish between cats and ducks, then use this model on a new data set with a high level of accuracy.
For large retailers, the application of this method could be very beneficial. With so many new images added to the inventory every day, and with visual search on the rise, a scalable image labeling system would prove very profitable. As demonstrated at TechSEO Boost, this is now a very realistic possibility for businesses willing to build their own model.
A further use of machine learning described by Britney Muller was the transcription of podcasts. An automated approach to this task can turn audio files into something much more legible for a search engine, thereby helping with indexation and ranking for relevant topics.
Muller detailed an approach using the Amazon Transcribe product through Amazon Web Services to achieve this aim.
The audio is broken down and delivered in a J-SON file in a lot of detail, with the different speakers on the podcast labelled separately.
There was not enough time in the session to work through every potential use of machine learning for SEO, but Muller’s core message was that everyone in the industry should be working towards at least a working knowledge of these concepts.
Some further opportunities for experimentation were listed as follows:
As we can see, machine learning truly excels when working with large data sets to identify patterns.
Tools and resources
The best way to get engaged is to combine theory with practice. This is almost always the case, but it is a particularly valid piece of advice in relation to programming.
Muller’s was not the first or last talk to reference Google Codelabs throughout the day.
There are more resources out there than ever before and the likes of Amazon and Google want machine learning to be approachable. Amazon has launched a machine learning course and Google’s crash course is a fantastic way to learn the components of a successful project.
The Google-owned Kaggle is always a great place to trial new data sets and review the innovative work performed by data scientists around the world, once a basic grasp has been attained.
Furthermore, Google’s Colaboratory makes it easy to get started on a project and work with a remote team.
Key takeaways: machine learning for SEOs
What became particularly clear through Muller’s talk is how approachable machine learning applications can be for SEOs. Moreover, the room for experimentation is unprecedented, for those willing to invest some time in the discipline.
Q4 is right around the corner, and that means digital marketers need to be on top of their game in planning, building, executing, and converting. But when you are looking to really scale revenue and new customers this holiday season, you’ll have to incorporate some branding strategies.
Now, I work for a performance digital marketing agency, so everything we do is always tied back to the question, ‘Well, is it improving performance?’ So when I say branding, I’m talking about the avenues that will allow you to get very targeted so that you can be sure you are hitting relevant audiences for your business. Better yet for performance marketers, there is a way where (to some extent) you can measure the effects these branding plays have on performance (I’ll get to that in a bit).
In this post, I’ll break down channels to test for branding, and then I’ll talk about how to measure the performance of those branding channels/campaigns. Let’s get started.
This channel has huge reach, and it’s a great way to cast a wide net and get exposure for your brand. The biggest downside with YouTube is that, if you’re not careful, you can spend a lot of your budget ineffectively.
Here are a few targeting recommendations to effectively get in front of the right audiences and have a positive impact on performance:
- In-market audiences – With this targeting, Google identifies users who are actively shopping for certain categories. Additionally, if you know the demographics of your target audience, you can layer on gender and age targeting to get more selective about the folks who see your ad.
- Custom intent audiences – You can also take things one step beyond in-market audiences and develop your own custom intent audiences. With custom intent audiences, you enter a list of search terms that align with what your ideal audience uses to find your product/service. Google will then use that list to define and reach the ideal audience for your business; this lets you go beyond Google’s predefined audience segments and reach people as they’re making a purchase decision.
What makes Instagram’s stories feature so great is that it takes advantage of all of Facebook’s granular targeting capabilities, which means you can get right in front of the specific personas you want to target (including interests, demographic, behavioral, as well as lookalikes and custom audiences). You can also get specific with the devices you want to target, so if you know, for instance, that your core purchasers are typically iPhone users, you can limit targeting to those devices.
I would recommend initially starting off with your top-performing Facebook audience and refine testing from there.
Native is a great way to deliver your ads to massive audiences who are in the mindset of consuming content. Native offers tons of channels: Outbrain, Taboola, Yahoo Gemini, etc. My recommendation is to start with Yahoo Gemini – in particular, the following ad types.
Yahoo mail ads appear within your Yahoo mailbox. You can leverage Yahoo’s capabilities to target by age, gender, interests, and custom audiences. Typically, I recommend targeting users interested in your competitors as they would be highly relevant; that, coupled with layering on age/gender data, will get you close to the personas you want to go after.
Additionally, as you test across Yahoo’s wider network with native, one highly recommended ad format to use would be carousel ads, which come in either desktop or mobile format.
Desktop carousel ads allow advertisers to show a more premium format for their ads:
Mobile carousel ads allow advertisers to use up to 5 images to tell a visual story:
One caveat: not all sites are set up to take carousel ad formats. The sites that are set up for carousel ads tend to be higher-quality properties, so it’s a nice bit of self-selecting when you put carousel ads into play.
How to measure branding performance
Okay, now that you’re casting a wide net and building awareness for your brand, how can you quantify the value of those efforts? Although it’s not easy to assign value to every aspect, we’ve found some strategies to be helpful.
One technique we use is by tagging our ads with utm parameters, indicating the channel, campaign, targeting and ad that a user is coming through on when they click the ad.
Then we develop remarketing campaigns or ad sets specifically targeting our brand awareness efforts. (For example, we remarket specifically to those who have clicked on our Instagram Story ad.) This separates our brand awareness efforts within our remarketing campaigns, which allows us to quantify conversions (and conversion rates) of those who have been exposed to our brand via our broader branding initiatives. It’s not perfect, but it helps us define how successful our branding efforts are.
With users brought in through branding campaigns, it’s important to remember that the buying journey can be longer – even if you’re a retail brand in Q4. If you’re looking to capitalize on your user base for the holiday season, there’s no time like the present to bring in this new audience and get the nurture/remarketing engine running.
Understand when it can become cost-effective to shift budget dollars to social app campaigns during periods of peak interest.
Read more at PPCHero.com
Optimizing e-commerce websites can be a bit overwhelming, especially when struggling through post-holiday blues. Check out some examples of how to approach your e-commerce optimizations.
Read more at PPCHero.com
In this new live webinar, Hanapin experts Jacob Brown and Tanner Schroeder will walk you through vital tips you need in order to optimize your online education programs and rest easy knowing that your enrollment numbers are where you want them to be.
Read more at PPCHero.com
Google’s new promotion extension is on its way to becoming one of the best ad extensions in an ecommerce PPC advertiser’s toolbox.
Read more at PPCHero.com
By now, large multi-location brands hopefully understand the importance of a local digital marketing strategy to ensure their many locations can easily be found online and help generate local leads.
What do most people know about Oklahoma? They probably know the title song from “Oklahoma!” It was the first musical written by the team of composer Richard Rodgers and librettist Oscar Hammerstein II.
The US Patent Office has just published a new patent application by Apple (via AppleInsider) that integrates crowdsourced traffic data for real-time information about road conditions, similar to what Waze does. Waze, which was just acquired by Google, seeks user input on changing road conditions, and rewards users for making accurate reports. Apple’s patent also offers route choices based on criteria like “Scenic Route, Light Traffic, No Construction” and more that are also rated and reviewed by users.
After months of speculation, the fate of Waze, the social-mapping-location-data startup, is finally decided: Google is buying the company, giving the search giant a social boost to its already-strong mapping and mobile businesses. Although speculation has had it at $ 1 billion, so far there is no price on the deal. It’s a doubly strategic move.
- Citizens Reserve is building a supply chain platform on the blockchain
- Tips to maximize ROI on paid social: Facebook + Instagram
- The case against behavioral advertising is stacking up
- Fender American Acoustasonic Telecaster: Pricing, Specs, Release Date
- The Newest Amazon Sponsored Products Features of 2019