Google uses over 200 different factors to determine where a website ranks when users enter a search term into their browser. While Google has always been secretive about the complete list of factors used by their algorithm, they recently disclosed the three most significant signals used to determine rankings.
The importance of RankBrain in Google’s algorithm was confirmed in October 2015. Recently, during a live Q&A with WebPromo, Andrey Lippatsev, one of Google Ireland’s senior strategists confirmed that the other two highest ranking signals were on-site content, and backlinks pointing to a site.
While this revelation will come as no surprise to most internet marketers, who have widely assumed the relevance of these factors for years, what was most surprising about the interview was how open Lipattsev was with his answers. Google usually operate in a very secretive manner, keeping their cards close to their chest.
Lippatsev went further into the interaction of these signals. When questioned about the order of the 3 most powerful ranking factors, Lippatsev declared that “there is no order.” This is an interesting response to what on the face of it, was a straight-forward question begging a straight-forward answer. By analysing his response we are left to assume that RankBrain’s influence on search rankings is dependent on its current pool of knowledge, and understanding of language.
Before we delve any further into the interview, we should look a little closer at what RankBrain is, and how it works. RankBrain’s primary function is to support the algorithm in delivering the most relevant search results to the user. It operates as an on-going learning system, evaluating and interpreting new data against a huge data-set to establish the users intent with their search. It does this by taking a search term it is unfamiliar with, and attempts to match the search with similar words or phrases to assist the algorithm in providing its search results.
Google had previously announced that RankBrain was the third most important ranking factor, but Lippatsev’s answer now suggests that it’s influence in the algorithm changes depending on what the artificial intelligence system has learned in relation to a particular search term. Lippatsev continued to explain:
“If you look at a slew of search results and open up the debugger to see what has come into play to bring about these results, certain things pop-up more or less often. Certain elements of the algorithm come into play for fewer or more cases. If you do that, you may see elements of RankBrain having been involved.”
This suggests that RankBrain’s influence in the algorithm is likely to increase as it develops its understanding and learns to deal with newer search terms. He also explained how Internet Marketers attempts to fully comprehend the algorithm in order to assist their own marketing needs was largely futile:
“It’s not like having three links is ‘X important’ and having five keywords is ‘Y important’, and RankBrain is some ‘Z factor’ that is also somehow important, and if you multiply it all together [you’ll understand how your page is ranked] it’s not how it works.”
Google’s ultimate goal with RankBrain is to move away from more formal search terms, and attempt to understand natural language to determine the intent behind the user’s search. This focus is what led to Google’s most recent major algorithm change, named Hummingbird. While the Hummingbird algorithm has continued to evolve in the 2 and a half years since its introduction, the artificial intelligence side is still in its infancy.
One of the areas driving this development is the increasing use of Mobile search, and in particular Voice search. It is still common when entering a search term into a mobile device to use a mechanical type of language as the user attempts to assist the algorithm understand what is required. As RankBrain continues to develop its artificial learning, Google expect that entering a voice search into a mobile will one day be no different than asking a question to a friend.