Rank Brain is an artificial intelligence (AI) program used to help process Google search queries.
RankBrain uses artificial intelligence to embed vast amounts of written language into mathematical entities, called vectors, that the computer can understand.
If RankBrain sees a word or phrase it isn’t familiar with, the machine can make a guess as to what words or phrases might have a similar meaning and filter the result accordingly, making it more effective at handling never-before-seen search queries.
In practice, for a search phrase like “How many tablespoons in a cup?”, Google’s Rank Brain will show different search results based on things like what country the search was made from.
Google told Search Engine Land that RankBrain favoured different results in Australia versus the United States for that query because the measurements in each country are different, despite the similar names.
And it’s effective: Google search engineers were asked to look at some pages and guess which ones they thought Google’s search engine technology would rank at the top of search results.
While Google search engineers guessed correctly 70 percent of the time, Rank Brain had an 80 percent success rate.
Overall, Rank Brain is capable of learning and recognizing new patterns and then revising SERPS (search engine results page) based on its new knowledge.