Pinterest Boosts Related Pins Using Deep Learning

Information technology'due south easy to get lost in the blackness pigsty of Pinterest Related Pins: One DIY project begets a hundred DIY projects begets a hundred DIY projects, and and so on—until information technology's midnight and you lot still need to feed the cat.

Oddly, 'related' oft seems a relative term for Pinterest as it previously used what it calls lath co-occurrence to generate suggestions. Basically, a pin is saved to many boards, so the related pins are drawn from that subset of boards.

The digital pinboard, yet, is stepping further into the 21st century by adopting a deep learning system to make Related Pins "even more relevant," Software Engineer, Kevin Ma, promised.

Pinterest AI Pin2Vec board co-occurrence

"We adult a scalable organisation that evolves with our product and people's interests, so we can surface the most relevant recommendations," he wrote in a blogpost.

For years, Related Pins have been generated based on other boards to which they were pinned. But while board co-occurrence provides infinite candidates to recommend, it can as well miss the mark.

"Board co-occurrence can lose the context of a Pin, so we needed a style to ameliorate understand pins and their relative relationships to pinners," Ma said, describing the Pin2Vec arroyo to embed pins in the context of users' activity.

While Pin2Vec is "a big footstep in improving the relevancy of Related Pins [and] an important source for generating candidates," Ma said, information technology does non replace lath co-occurrence.

"Looking ahead, nosotros're already making our models faster and analyzing more signals to better personalise recommendations for pinners around the world," he added.