From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search

TL;DR

This paper presents deep learning models for semantic retrieval and pairwise re-ranking in e-commerce search, significantly improving relevance and personalization over traditional methods.

Contribution

It introduces a deep learning system for fast semantic retrieval and a pairwise re-ranking model to better capture user preferences in e-commerce search.

Findings

Achieves faster retrieval within milliseconds.

Improves relevance and personalization over traditional systems.

Significant performance enhancements demonstrated.

Abstract

We introduce deep learning models to the two most important stages in product search at JD.com, one of the largest e-commerce platforms in the world. Specifically, we outline the design of a deep learning system that retrieves semantically relevant items to a query within milliseconds, and a pairwise deep re-ranking system, which learns subtle user preferences. Compared to traditional search systems, the proposed approaches are better at semantic retrieval and personalized ranking, achieving significant improvements.