Here’s how Google is using machine learning to improve Chrome

Here's how Google is using machine learning to improve Chrome

Google on Thursday shared a few ways it’s using machine learning to improve the Chrome browser, including reducing the number of annoying notifications that appear.

The latest updates are all powered by on-device machine learning models, so user data doesn’t have to leave the device.

For a less disruptive web browsing experience, Google uses machine learning to determine when a user might want to interact with a notification permission request. In the next version of Chrome, the browser will use an on-device model to predict how a person is likely to react to a permission request. If the user is likely to reject it, the browser will silence it. The prediction is based on how the user has reacted to similar permission requests previously.

Security and Toolbar

Google also said that in March it used the ML model to improve the Safe Browsing in Chrome feature, which displays warnings when people try to browse to unsafe sites or download dangerous files.

The new ML model for this feature identifies 2.5 times more potentially malicious sites and phishing attacks than the previous model.

Google also uses the ML model to create a dynamic Chrome toolbar, with tools that change in real time based on your needs. For example, if you are in a situation where you want to use the touchscreen to share a link, the share icon will be in the toolbar. If you’re more likely to use voice search on Chrome, the toolbar will highlight the voice search tool. The toolbar will still be customizable manually.


Leave a Comment