RankBrain is a system developed by Google that uses machine learning and artificial intelligence to improve search results and interpret new search requests, that is, terms that have not been surveyed previously. Some experts consider that RankBrain is part of Hummingbird’s search algorithm.
Hardly anyone of the digital industry has not heard of RankBrain. It is no coincidence that this system, apart from huge impact on search results, because many questions and discussions.
We made an attempt to understand how the RankBrain works and if there is something that can be done to optimize and prepare the site for the meeting with him. Let’s start at the beginning.
Some experts consider that RankBrain is part of the search algorithm Hummingbird , which was launched to help Google better understand the meaning of search requests expressed by exact keywords.
The RankBrain was first mentioned on October 26, 2015 by Greg Corrado, senior research analyst Google. That’s how Greg explained the operating principle of the algorithm:
“If you are searching for an ambiguous phrase, using colloquial terms or talking to Google as if it were a person, often the computers can not process this request not understand the request or never have seen before. The RankBrain can generalize the phrase: ‘This sentence looks like something I’ve seen in the past, so I consider it was just that you wanted to know.’ It’s like a person talking to you in a crowded bar -. They can not hear everything you say, but even so they can guess what you mean and continue the conversation with you “
In this interview, Greg also said that soon after the launch, the RankBrain became the third most important ranking factor. Since it has such an impact, it is important to understand exactly how this algorithm works and what changes it can bring to users and expert SEO .
As I said earlier, the main objective of RankBrain is to deliver the most relevant results, playing the full meaning of the phrase instead of focusing on individual words. This algorithm can cope well with search requests complex long tail, understand how they are connected to specific topics and provide relevant results.
In a nutshell, RankBrain identifies patterns in different search requests (even those that seem completely unrelated) and finds similarities between them. This allows the Google search engine understand a phrase never seen before simply making a correlation with phrases already known by the robot.
Being a system of machine learning, the RankBrain autoaprende constantly probably paying attention to the metric (eg bounce rate or time spent on the page). That is, if a user believe that the results are not relevant, the next time the algorithm will show other results for this search.
Google does not share exact algorithms it uses, however we know that the principles of his operation are similar to those of word2vec tool .
Word2vec is an open source toolkit that uses the text of the body to calculate the distance between words and produce the vector representations of words and phrases.
This helps to understand the relationship between words based on the distance between them in the texts. Words with similar meaning are close to each other (in vector space). Chris Moody describes a test in order to find the nearest vectors the vector word “vacation”.
To learn more about word2vec and his operating principles, check out A Beginner’s Guide to word2vec (A Newbie’s Guide word2vec), written by Distilled. If you are interested in more technical details, read the tutorial Vector Representation of Words (Representation of words in vectors), written by TensorFlow.
We wanted to gain a deeper understanding of how the RankBrain works and, therefore, did an experiment. We try to build connections between words using the word2vec algorithm and data SEMRush (texts obtained from the Brand Monitoring Tool ). For more clear results, only process the bodies of texts related to Digital Marketing and SEO.
In the end, we had a tool that can be used to enter any branch of the word Digital Marketing and get a list of words that are more related to the initial word. Not exactly “synonyms” (that is, words that have similar meaning) or “related words” (words that bring similar search results in search machines). This is something completely different – are words that appear more in the texts in conjunction with the word entered.
With our experiment, we try to understand how Google “thinks” and what words he considers related to the keywords you are targeting. The results were very interesting and at the same time were not anything close to expected.
To begin with, we did a survey of Digital Marketing specialists, asking to give three associations to a few words and then compared the results with those obtained with the help of the tool. We noticed that not all the words that are most associated with certain concept appear side by side in the texts:
According to the official representatives of Google, there is a way to optimize for RankBrain . And more – the RankBrain will have drastic effect on search results, because the main objective of the algorithm is to handle searches for which data are lacking .
Another point – as I said on Twitter Gary Illyes, search analyst Webmasters, “the RankBrain also has no influence on crawling and indexing.”
However, it would be unwise to simply ignore the existence of a powerful algorithm in their SEO activities. So what conclusions can we draw on the operation of RankBrain algorithm?
Nothing to create pages and content optimized for a keyword or keyword phrase only. For maximum effect, try to include in your semantic core these elements:
Write more complete posts, try to talk about all aspects of the chosen topics, answer as many questions as possible. The ultimate goal of Google and RankBrain is to ensure that users get the best and most relevant results. If you share the same goal, you will have more chances to succeed.
Even if this advice may seem trivial, it is especially true in cases of machine learning. As Neil Patel said in his article :
“It’s called machine learning because the machine learns not only of abstract environmental forces, but mainly from the behavior of human beings.”
That is, there is no point trying to please the search algorithms. Focus on providing a better experience for your users, analyze their behavior and make optimization agreement. If people come to appreciate its contents and consider it relevant, the algorithms will do the same in a natural way.
To conclude, our attempt to understand one of the most mysterious algorithms Google demonstrated that it is almost impossible to intuitively predict how Google thinks. To make matters worse, being a machine learning system, it is constantly developing. At the same time, Google’s algorithms are being updated and optimized.
All you can do to get follow these constant changes is to make sure that is always being competent and committed in everything they are doing or writing. This, so you will succeed whatever the new algorithm or update that appear on the market.