Optimize for RankBrain?
Guest blog by Romano Groenewoud from SEOgeek
RankBrain is one of the most new and interesting algorithms that Google has recently used to get the best search results. RankBrain is mainly used for optimizing search results in Google by converting typed punctuation marks into sentences that the computer, and Google, can understand. In short, RankBrain is therefore just like the human brain: it sees, it decodes and organizes, and then gives a hopefully (sufficient) answer. decoded and organized. Does the search make sense?
RankBrain is at its best here: it is able to turn unfamiliar words and phrases into meaningful sentences that Google can understand. But there is a slight difference with the human brain: RankBrain is not the main processor of information. RankBrain serves as a 'helper', and really only comes in handy when Google's search results are not optimal, or are in fact not properly 'decoded'. When Google doesn't understand something, RankBrain comes to the rescue. It then acts as an artificial intelligence algorithm and organizes the searches in a different way. Ultimately, but that's science for later, RankBrain wants to evolve into being able to recognize phrases that basically say the same thing:
“What are the best movies on Netflix?”
“What are Netflix's top movies?”
“Which movies are the best to watch on Netflix?”
Basically, these questions ask: What's the best thing to watch on Netflix? All the same question. Until now, Google doesn't recognize this, and you get different results for every question, but RankBrain will be used for recognizing that these questions mean the same, so that they can return the same.
But for now, RankBrain delivers better search results to Google in several ways, and has recently become Google's third most important ranking factor. It is therefore not surprising that the question arises:
How to optimize for RankBrain?
According to the 2015 Bloomberg report and Google spokespersons, RankBrain guarantees 15 percent of Google's never-before-seen searches every day. RankBrain is also a largely independent algorithm (Deep Learning) that develops itself further, without human input. An example of this is, for example, this Deep Learning algorithm created by Google that gradually develops into a super player during the game:
There's only one thing you can do to optimize for Google: meaningful and understandable texts to write. But optimizing for RankBrain is a bit more complicated. RankBrain, from what we know so far, is mainly a player in the organization of sentences and thus is aimed at learning to better understand language. So the answer to the question is succinctly, and clearly:
There is no single way to optimize for RankBrain.
Guessing about signals
In addition to some factual statements from prominent sources regarding RankBrain and Google, there is ambiguity and obscurity about the precise signals and vectors that RankBrain uses to understand complex language. Vectors are the mathematical entities that are the big meaningful texts, and are actually the foundation of RankBrain. The clearer the vectors, the better Google understands what is being searched for, and thus the better the search results will be. A Google spokesperson does not want to make a direct link to Word2Vec, a prominent vectors model, after research, but it is widely suspected among techies that Word2Vec is the basic model of RankBrain. The Google spokesperson does want to indicate that it is 'related to Word2Vec', and that it can therefore be a layer of RankBrain.
The ambiguity about which signals RankBrain uses is explained by Rand Fishkin (co-founder of Moz.com, see here) somewhat contradicted. He states that RankBrain deals with the main signals Google uses, specifically:
- Freshness of the content (is it a repeat of last year's news, or is the content real'new new' and, does it look fresh?)
- Participation (Commitment, an important signal for Google)
- Depth of content (cut the wood, isn't it bullshit?)
And to a lesser extent:
- Keywords and Keyword Matching (key words within the text)
- Domain Quality (Google doesn't want to be overloaded by low quality domains)
These are pretty much the most important signals for Google, and RankBrain mixes in by helping Google what the most important signals are and how to actually "weight" those signals. RankBrain selects and prioritizes certain signals, but still, because RankBrain attaches little value to, for example, keywords and other signals, according to Rand Fishkin, optimizing for RankBrain is not just possible, according to him. In addition, RankBrain is one of hundreds of 'signals' that Google uses to build an algorithm, and although we know that RankBrain is widely used, it is not clear exactly how big the influence of the other signals is.
Still, we can somewhat infer from Rand Fishkin's words that when you look at the main signals from Google, partial optimization for RankBrain is possible. But then again, isn't that just optimizing for Google?
SEO Will do the trick
It won't make many people happy, but: the ambiguity about signals and the vector models that RankBrain uses make optimization impossible. It is impossible to find out which words use the best vectors so that you end up a little higher in the search results. So optimizing for RankBrain is difficult. Some people argue that this is the # death of SEO, but rest assured: Google says the SEO magic is not over and that good and clear writing still makes the most of it. That is also the most important message: deliver good writing and do not expect RankBrain to translate everything into meaningful sentences, content, depth and participation are the most important.