HomeGame GuidesGoogle Chrome's search bar is now powered by machine learning to make...

Google Chrome’s search bar is now powered by machine learning to make better suggestions

Published on

In an official blog, Google announced a new update to the Chrome browser that brings some new changes to the search bar. According to Google, the new update should help the address bar, also known as the Omnibox, to provide more ‘accurate and relevant’ web page suggestions.

The Mountain View-based company said that with the latest Chrome update (M124), Google integrated machine learning models into the address bar or search bar. Machine learning will help Chrome deliver accurate suggestions tailored to what you’re looking for.

Google says the browser previously relied on ‘hand-built and hand-turned formulas’ to suggest search results. However, the main problem with this was that these were not flexible enough to bring about improvements or to adopt in new scenarios.

With the new machine learning models embedded in Chrome’s search bar, Google can “collect more recent signals, retrain, evaluate and deploy new models” as time goes on. Since the number one answer when asked for ideas to improve the address bar was ‘improve the scoring system,’ the adoption of machine learning in the search bar is a big deal because, as Google noted, “the scoring system has been largely untouched for a long time.”

According to Google, a machine learning model in Chrome’s address bar will take into account your previous actions on a URL when suggesting a web page. That is, if you’ve navigated away from a web page in the last few seconds or minutes, the machine learning model will rate that web page lower based on its understanding that it’s not the site you were looking for.

Going forward, Google believes this new machine learning model will open up “many new possibilities for improving the user experience by potentially incorporating new signals, such as distinguishing between the hours of the day to improve relevance.”

In addition, Google says that the relevance scoring system needs to change over time, and thanks to the new scoring system, it can now “simply collect fresher signals, retrain, evaluate and deploy new models periodically over time” for better results.

Latest articles

More like this