Gary Illyes: How RankBrain Works


Jun 28, 2012
Google's Gary Illyes Explains How RankBrain Works
Search Engine Journal
Feb 8, 2019


RankBrain. Lots of people keep saying that part of the RB system includes UX signals, including Dwell Time, Bounce Rate, Click Through Rate, etc.​
As I understood it, RB was about trying to fathom what results to serve for unrecognized searches. Can you please confirm/deny whether RB uses UX signals of any kind?”​

Illyes explained that RankBrain uses search data to predict what a person might click on when searching for something that hasn’t been entered into Google before.

“RankBrain is a PR-sexy machine learning ranking component that uses historical search data to predict what would a user most likely click on for a previously unseen query.”​

He goes on to state that RankBrain frequently solves problems that Google used to run into with traditional algorithms.

Also, RankBrain relies more on data gathered from users’ interactions with search results, versus users’ interactions with a piece of content.

In his words:

“It is a really cool piece of engineering that saved our butts countless times whenever traditional algos were like, e.g. “oh look a “not” in the query string! let’s ignore the hell out of it!”, but it’s generally just relying on (sometimes) months old data about what happened on the results page itself, not on the landing page.”​

Lastly, Illyes calls out those who overcomplicate things and theorize that RankBrain uses on-page signals.

“Dwell time, CTR, whatever Fishkin’s new theory is, those are generally made up crap. Search is much more simple than people think.”​
Thread starter Similar threads Forum Replies Date
djbaxter Organic SEO 4
Dustybones Local Search 6

Similar threads

Local Search Forum

Weekly Digest

Google Product Exert


Join Our Facebook Group