Google adds machine learning smarts to Gmail's spam filter

Google took to a blog post today to talk about some improvements that it is bringing to its spam-fighting engine in Gmail. The company says that the improvements largely rely on applying the same machine learning from Google Search and Google Now to the Gmail spam filter.

Here's the breakdown of the improvements Google is bringing to the spam filter in your inbox:

  • For starters, the spam filter now uses an artificial neural network to detect and block the especially sneaky spam—the kind that could actually pass for wanted mail.

  • We also recognize that not all inboxes are alike. So while your neighbor may love weekly email newsletters, you may loathe them. With advances in machine learning, the spam filter can now reflect these individual preferences.

  • Finally, the spam filter is better than ever at rooting out email impersonation—that nasty source of most phishing scams. Thanks to new machine learning signals, Gmail can now figure out whether a message actually came from its sender, and keep bogus email at bay.

Additionally, Google also detailed a new set of tools for companies that send out a large number of legitimate emails. Gmail Postmaster Tools allows "qualified high-volume senders" to keep track of their emails — including spam reports and reputation — and more easily identify where they may be falling short.

Source: Google