Rethinking Personalized Ranking at Pinterest: An End-to-End Approach

TL;DR

This paper introduces an end-to-end personalized ranking system at Pinterest that leverages raw user actions to improve long-term and short-term recommendations, demonstrating significant online performance gains.

Contribution

It presents a novel integrated model architecture combining long-term user interest encoding and real-time action learning, optimized for production deployment.

Findings

Significant online performance improvements at Pinterest

Effective encoding of long-term user interests

Successful deployment in production environment

Abstract

In this work, we present our journey to revolutionize the personalized recommendation engine through end-to-end learning from raw user actions. We encode user's long-term interest in Pinner- Former, a user embedding optimized for long-term future actions via a new dense all-action loss, and capture user's short-term intention by directly learning from the real-time action sequences. We conducted both offline and online experiments to validate the performance of the new model architecture, and also address the challenge of serving such a complex model using mixed CPU/GPU setup in production. The proposed system has been deployed in production at Pinterest and has delivered significant online gains across organic and Ads applications.