The Simplified Guide to Google’s RankBrain Algorithm

Not so long ago you had to search for a term like “Boston restaurants” to find a place to eat. But today, if you just search for “where should I go for dinner”, you can instantly find a good restaurant nearby. Search.

This is because Google is sophisticated enough to recognize your intent or the implications of your request. Before 2015, however, you had to type the simplest of queries into the search engine to find the answers you were looking for.

How has Google evolved to understand the intentions and implications of their searchers so quickly? On October 26, 2015, they confirmed that they had updated their algorithm with an artificial intelligence machine learning system called RankBrain.

In other words, RankBrain helps Google understand a searcher’s intent and serve them the most relevant content.

How does Google’s RankBrain work?

As explained above, RankBrain is specifically designed with the searcher’s experience in mind, especially when it comes to understanding the intentions and relationships behind seemingly complex searches.

To better explain this functionality, the way RankBrain works is explained in connection with the entire Google algorithm:

RankBrain and other ranking signals

Before RankBrain, Google used a number of ranking signals to determine:

• relevance to the search query
• The authority a specific website and page to give a trustworthy answer
• User experience so that the seeker can meet his needs in a pleasant way and without friction

Some of these signals (or ranking factors) include:

• Crawlability / indexability
• Quality content
• Backlinks
• Page speed
• Mobile experience

While these ranking factors are still relevant, they no longer tell the full story. On the one hand, they are largely static and do not take into account the semantic search. This is where RankBrain differs from these components of the Google algorithm.

RankBrain and machine learning

Machine learning is a form of artificial intelligence that “learns” from data and improves based on experience. The advantage of machine learning is that it can analyze and combine a wide variety of variables to “understand” what a human analyst cannot – when they have enough data.

Why is this relevant in the context of RankBrain? Because RankBrain is an example of machine learning as implemented by Google.

To pinpoint a searcher’s intent, Google feeds RankBrain with a huge amount of data. RankBrain then analyzes it and teaches itself how to deliver the most relevant results based on certain search signals like search history, device and location.

For example, if you asked, “Where should I go for dinner?” Enter. In Google, the search engine first determines your location and recognizes the device you are using. These factors are then used to interpret the intent of your request. Google translates this to “What restaurants are currently open for dinner within walking distance of my current location?” To bring you the most relevant results.

RankBrain and Hummingbird

Hummingbird is a version of the Google search algorithm that extracts the meaning of the entire query, not specific words. This component is why Google can determine semantic meanings from certain queries to get the best result.

RankBrain feeds user signals into this aspect of the algorithm, improving Google’s ability to infer the meaning. To better describe the relationship between the two, Connectica makes the following analogy: “RankBrain is thinking and Hummingbird is memory.”

An example of how RankBrain works in this way is how similar the search results are for semantically similar but different keywords. For example, “Bangs” and “Bangs” have similar results, including keywords that are not word-for-word optimized for the specific query.

Image source

How do you optimize for RankBrain?

Although RankBrain is helping Google adapt to changing search behavior, most marketers have not yet adapted their SEO strategy to this transformation. Here are some mindset changes that you should adopt when considering modern SEO.

1. Don’t just think about keywords anymore.

“One of the main reasons we keep engaging our audiences with the idea of ​​topics over keywords is because search has evolved, but our clients’ content marketing strategies are lagging,” said Victor Pan, HubSpot’s head of technical SEO with misspellings and poor grammar just because the search volume has to go. “

These days, users rely heavily on Google for accurate and relevant answers to most of their questions. Hence, the search engine needs to understand the intent and context behind each and every search.

To this end, Google developed to identify current connections between user queries, look back on similar queries that users have searched for in the past, and display the content that best answers them. As a result, Google delivers content that is most relevant to the topic.

2. Implement the pillar cluster model.

To help Google recognize your brand as a trusted authority, implement the pillar cluster model on your blog. With this strategy, you create a single column page that provides a high-level overview of a topic and hyperlinks to cluster pages that deal with the topic’s subtopics. This signals to Google that your columnar page is an authority on the matter.

Linking all of the cluster pages to the column page also distributes domain authority in the cluster, so your cluster pages get an organic boost if your column page ranks higher, and your cluster pages can even help your column page rank higher if it is ranked for the specific Keyword they are targeting.

3. Move to long, high quality pages and posts.

On the editorial side, RankBrain has pressured content marketers to ditch a tactic they should have given up years ago – prioritizing volume over quality. Today, one of the best ways to build your reputation on Google is to spend more time and effort creating insightful, compelling, lower-volume content.

“If you have a large inventory of SEO tactics dating back to 2000, I would highly recommend consolidating the pages that are of no value to your business with 301 redirects,” says Pan. “It’s not that less is more, but better is more.” It is very common for strong content to rank for over hundreds of long-tail keywords with the same intent. “

RankBrain has expanded the Google search engine to the point where users can interact with it as if they were chatting with their friends – and it’s time for content marketers to catch up.

However, if you apply the lessons learned above to your SEO strategy, you can adapt to RankBrain faster than the search algorithm developed by Google after implementing the AI ​​system.

Editor’s note: This post was originally published in April 2019 and has been updated for completeness.