How machine learning in G Suite makes people more productive

Eliminating spam within Gmail using machine learning

One of the earliest machine learning use cases for G Suite was within Gmail. Historically, Gmail used a rule-based system, which meant our anti-spam team would create new rules to match individual spam patterns. Over a decade of using this process, we improved spam detection accuracy to 99 percent.

Starting in 2014, our team augmented this rule-based system to generate rules using machine learning algorithms instead, taking spam detection one step further. Now, we use TensorFlow and other machine learning to continually regenerate the “spam filter,” so the system has learned to predict which emails are most likely junk. Machine learning finds new patterns and adapts far quicker than previous manual systems—it’s a big part of the reason that more than one billion Gmail users avoid spam within their account.

See machine learning in your favorite G Suite apps

G Suite’s goal is to help teams accomplish more with its intelligent apps, no matter where they are in the world. And chances are, you’ve already seen machine learning integrated into your day-to-day work to do just that.

Smart Reply, for example, uses machine learning to generate three natural language responses to an email. So if you find yourself on the road or pressed for time and in need of a quick way to clear your inbox, let Smart Reply do it for you.