Pinterest Resorts to Deep Learning to Help with the Generation of Related Pins

In order to help generate better Related Pins, Pinterest has decided to switch from board co-occurrence to deep learning. This is because Related Pins is one of the most sought after and popular ways in which people find relevant ideas. Related Pins uses a collaborative filtering system that would work by using co-occurrence signals from the different boards Pins are saved to. However, now this web and mobile application company is moving to a more advanced system of generating Related Pins by the application of deep learning. In an official blog post, Pinterest software engineer Kevin Ma, who works for the Discovery team, stated, “Previously, candidates were generated using board co-occurrence, signals from all the boards a Pin is saved to. Now, for the first time, we’re applying deep learning…


Link to Full Article: Pinterest Resorts to Deep Learning to Help with the Generation of Related Pins

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about homeAI.info and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!