Share

Gmail Now Has An ‘Artificial Neural Network’ For Improved Spam Detection

“Gmail users get lots of important email from companies like banks and airlines-from monthly statements to ticket receipts-but sometimes these wanted messages are mistakenly classified as spam”.

Advertisement

For years, Google has championed the act of reporting email spam-for the goal of helping users, the Gmail community, and internal development.

In an announcement made on Thursday, Google said that it is now fighting Gmail spam with the help of the same artificial intelligence which it developed for Google Search and Google Now. However, we all know that at some point you need to check spam because inevitably a message that isn’t spam ends up in there. However, its latest approach involves an artificial neural network, the same tech which the company deploys behind Google Now and Google Search.

From the beginning of Gmail, Google used machine learning in order to upgrade the spam filter, and relied on the 900 million users it has to mark the messages as spam by using the buttons “not spam” and “report spam”.

“We also recognise that not all inboxes are alike”. It’s now implementing machine learning to detect and block spam trying to pass off as wanted mail; Google says it’s smart enough to weed out phishing scams.

“So while your neighbor may love weekly email newsletters, you may loathe them”, Somanchi wrote. Postmaster Tools will also give senders more insight into their domain’s reputation (send a lot of spam and Gmail will downgrade you) and additional info about how Gmail treats their messages.

It’s on a good path, as now less than 0.1 per cent of email in the average Gmail inbox is spam, and the amount of wanted mail landing in the spam folder is even lower, at under 0.05 per cent. At least, that’s what Google says.

Advertisement

Google says, these new filters are very much better at making out the individual preferences.

Google Improves Gmail's Spam Filters, Launches New Analytics Tool For Bulk