Opinions About Machine Learning for SEO

Lazarina Stoy, SEO & Data Science Senior Manager, the queen of Machine Learning for SEO, is back at it again, shedding light on the best ways to put machine learning to use in your SEO efforts. The below excerpts are taken from O/SEO/O? E9: Opinions About Machine Learning for SEO where Lazarina discusses how to choose the best model per case, the difference between AI and ML, and how to use machine learning for redirect mapping in SEO.

Tory Gray: What's the difference between machine learning (ML) and artificial intelligence (AI)??

Lazarina Stoy: The difference is that machine learning is only a subset of artificial intelligence. Artificial Intelligence includes everything that is kind of a robust, thorough, end-to-end system. If we're just talking about machine learning, that is mathematical-statistical models combined with programming logic.

TG: How do you choose the right machine learning models for specific SEO tasks?

LS: [There are] so many models to choose from for every single task. Keyword clustering has definitely been one of the ones that has experienced a boom in the past few months. The way that I would go about choosing a model would be first to understand how it evaluates the similarity between certain keywords.?

So using the example of keyword clustering, you would like to see what keywords are similar to one another, and then find that core term that defines that cluster. Which one is the most definitive out of all of those for that group of keywords? And there are different methods to do this.?

TG: How can we use machine learning to find schema types for a website and implement them?

LS: The long and short answer is that yes, it's possible. But there are a lot of buts. When it comes to data science or trying to build any sort of program to do something for you, you can make it as easy or as complex as you'd like. If you have the word ‘recipe’ more than 10 times, then you can have a recipe schema. If you have a product or related semantic variation of the word ‘product,’ like ‘product description,’ ‘product size guide,’ or whatever else, that same kind of tool, or let's say the CMS, could recommend that type of schema.?

The challenge here and why it's a little bit hard to build especially as an external tool, I think as an internal tool would be a little bit easier because they have the capabilities for this. But as an external tool, you would have to then automatically generate the schema.?

TG: How can we easily use machine learning for redirect mapping in SEO?

LS: This is an application where fuzzy matching would be very good because, especially with redirect mapping, you would need to identify whether there is similarity in the URLs. And if you are also moving the URLs, you might need logic that reads the page as it's doing that.

It can sometimes be difficult to escape what you know and step outside of the box of your role in the industry. Lazarina breaks down machine learning applications for SEO in depth, and the best ways to put them to use.

Read the original article, or watch the full episode here.