Here’s how Google uses ML to improve Chrome
Google on Thursday shared some ways using machine learning to improve Chrome browser, including reducing the number of annoying notifications that pop up. All the latest updates are powered by on-device machine learning models, so user data doesn’t need to leave the device.
For a less disruptive browsing experience, Google is using ML to determine when a user might want to interact with the notification permission prompt. In the next release of Chrome, the browser will use on-device modeling to predict how a person is likely to respond to permission prompts. If the user has the ability to decline it, the browser will disable it. Predictions based on how users have previously interacted with similar permission prompts.
Google also noted that in March, they used ML to improve Safe Browsing in Chrome, which displays warnings when people try to navigate to dangerous websites or download dangerous files. The feature’s new ML model identifies potentially malicious websites and phishing attacks 2.5 times more than the previous model.
Google is also using ML to create a dynamic Chrome toolbar, with tools that change in real time in anticipation of your needs. For example, if you are in a situation where you might want to use the touch screen to share a link, the share icon will be highlighted in the toolbar. If you are most likely using voice search on Chrome, the toolbar will highlight the voice search engine. The toolbar will still be manually customizable.