Getting Started With Machine Learning In SEO With Lazarina Stoy

Our very own Lazarina Stoy was featured on the Rank Ranger blog/podcast! In this episode, Lazarina discusses the six steps to getting started with machine learning in SEO. Here are some highlights from the discussion.

The steps are as follows: 

1. Understand Your Limiting Beliefs and Overcome Them

This little step is about actually thinking about what's stopping you from actually pursuing machine learning a little bit more. What's stopping you from getting started with SEO automation and doing things that are fancy new scripts and tools and things like that. Because oftentimes, we hear a lot of people really inspired by new technology, and they want to try it. But they have these limiting beliefs that are stopping them from doing so.

2. Understand Common Task Specifications, Solution Specifications, and Data Specifications in Machine Learning

The three things that you need to think about are the data characteristics, task characteristics, and solution characteristics that you have. For data characteristics, think about the data set that you're going to apply machine learning to. In a beginner-friendly scenario most often this will be - textual, numeric data, or it can also be image-based data. The task characteristics will dictate whether you will be looking for a supervised or unsupervised learning, while the solution characteristics will define whether machine learning will be able to assist you in your task altogether. 

3. Practice Daily and Start Going Through the Motions

Daily practice is crucial. And it keeps you on your toes, specifically because it helps you find out what machine learning can do, essentially. And if you know what it can do, then when you get on with your daily role, it's going to be a lot easier for you to find opportunities to embed machine learning into processes. And I do want to highlight here, it doesn't mean that you should have fully automated solutions that work with the click of a button and you can fully automate your job. It means that if you can split the specific project that you're working on into 10 different bits, and if you can help yourself automating or embedding machine learning and maybe two of these 10, then you can have a lot more time to focus on the output of the rest of these 10 or work on career-advancing projects or your soft skills. 

4. Asses New Tasks, Their Solutions, and Data Characteristics to Understand When Machine Learning is Needed

When you are going through your role, and you have started getting some practice playing around with some scripts and models, you will find opportunities for embedding machine learning into tasks and processes. When you are encountering a given task, you can always go through some handy flowcharts and questions I’ve detailed in a blog post on my website about getting started with machine learning for SEOs, and assess whether machine learning will be a suitable solution for you in the task you are tackling. That way you can quickly understand when and how you can apply machine learning and what task you will need it as your ally for. 

5. Understand the Limitations and Scrutinize the Output of Machine Learning

Right now machine learning is at a stage where it's very good at narrow tasks.  If you are using pre-trained models, and you're not training them yourself, most of the time you're going to see that the data set that they have been trained on is not particularly useful to the particular industry, or it's not as in-depth as you might want it to be. And that's particularly the case for text-based tasks like NLP and things like that. Hence, it is good to test and understand the different tasks where machine learning can be useful and the others where it might not be as useful as you hope. When implementing machine learning always scrutinize the output. 

6. Work Collaboratively and Set Reasonable Expectations

This last step is all about knowing when you need help and knowing how to get the right help. And here I think there are a few things that you can pursue in order to get you the help that you need. First of all, find a machine learning buddy. Someone that is the same type of person as you. They work in the same industry. They have the same type of problems. And you're thinking and encountering problems and you're researching for tasks kind of together. And when someone finds something that's useful for the role, then they share it with their buddy. It helps you keep yourself accountable, it helps you keep yourself motivated and it genuinely is a very good thing to have.

 

To read or listen to the full episode, click here.