RankBrain: How it Works and Why it is Important

Assignment 3: SEO concepts – RankBrain

By: Lexi Babovac

What is it?

Google developed a machine-learning artificial intelligence technology, called RankBrain, to change the way Google searches are processed and delivered. The development of this technology, which was introduced by the company in 2015, has established RankBrain as one of the hundreds of signals that interpret the search engine’s queries. It helps Google determine what signals are most important to a query response, and interpret the query and searcher intent. In fact, according to Forbes, RankBrain has become the third-most important signal contributing to the result of a search query, according to the Bloomberg article.

RankBrain is part of Google’s overall search “algorithm”, which uses machine learning to determine the most relevant results to search engine queries. However, this computer program was created to go above and beyond determining which results to show for a given query, and now predicting the actual intent of the searcher. RankBrain is used to sort through billions of familiar web pages and find ones that are relevant for particular searches. It is actually the first system within Google’s search algorithm that uses machine learning to process high volumes of search queries submitted to Google. Essentially, when one submits an ambiguous question on Google, RankBrain is able to generalize the phrase based on its own machine-learned knowledge and is able to guess what words or phrases may have a similar meaning to what was typed in and filter the response accordingly. According to Mark Chalcraft, British writer for the UK, “Google states that approximately 15% of search terms have never been used before, and processing these queries to return more accurate and useful search results is one area that RankBrain is helping Google to improve”.

How RankBrain Works

The machine learning aspect of RankBrain is designed and manipulated by Google engineers. What makes this system unique from other updates is that it is able to work from Google inputting a surplus of knowledge and data from a variety of sources into the machine. The algorithm then calculates and teaches itself over time to match a variety of signals to a variety of results and to order search engine rankings based on the calculations. Clearly, its learning mechanisms are not continually operating, but rather being tried and tested by engineers to discover more accurate data.

SEO responses from Moz

We are not able to optimize for RankBrain itself, even though it is helping Google select which signal to prioritize when responding to a query. However, we are able to directly optimize the signals and have a personal opinion of what signals are more important than others. Ultimately though, we cannot do SEO for RankBrain specifically.

SEO concepts:

1. RankBrain encourages searchers to condense concepts, keywords, and URLs to a minimum in order to generate a response with one page that targets all of the intent being searched for. Modern SEO combines similar words or phrases together, in order to get a single piece of thorough content with the correct context of the searcher. RankBrain emphasizes the importance of focusing on full keyword concepts with collective content, instead of several pages to cover word variations.

2. It’s no longer the case that one set of fixed inputs no longer governs each query. This is due to the fact that nowadays people are looking for very specific results that demand signals that are not common or proportional to others. This fact has caused for the need of RankBrain to match signals to query intent. SEOs must match signals to query intent as well in order to determine what content best serves the searchers’ needs.

3. Signals apply to the website’s reputation. Domains gain a reputation from the signals put out by search engines and human users. It is important to build a reputation based on the signals you intend to serve. Specifically, RankBrain creates the ability to have one’s brand gain a reputation from a particular type of content for a certain need.

In conclusion, Google understands the importance of finding the searcher’s intent in order to find the context of the query, which is why RankBrain has been introduced. Making sure you capture the context is a key to optimizing for the machine learning approach. RankBrain has been researched globally for years and has hundreds of people working on R&D projects for AI like these. With the advancement of technology in the years to come, RankBrain and AI in general have a huge potential for future advancement on a very large scale.

Bibliography

Chalcraft, M. (2015, November 11). Google's RankBrain Explained – What It Is and What It Means for Your Business. Retrieved from https://www.freshegg.co.uk/blog/technical-seo/google-s-rankbrain-explained-what-it-is-and-what-it-means-for-your-business

DeMers, J. (2015, November 12). What Is Google RankBrain And Why Does It Matter? Retrieved from https://www.forbes.com/sites/jaysondemers/2015/11/12/what-is-google-rankbrain-and-why-does-it-matter/#4c3135c4536b

Fishkin, R. (2016, September 30). Optimizing for RankBrain... Should We Do It? (Is It Even Possible?) - Whiteboard Friday. Retrieved from https://moz.com/blog/optimizing-for-rankbrain-whiteboard-friday