Unified Embedding Based Personalized Retrieval in Etsy Search

TL;DR

This paper presents a unified embedding model that combines graph, transformer, and term-based methods for personalized product search, significantly improving search relevance and conversion rates in Etsy.

Contribution

The paper introduces a novel end-to-end trained unified embedding model for personalized retrieval, integrating multiple embedding techniques and innovative training strategies.

Findings

5.58% increase in search purchase rate

2.63% increase in site-wide conversion rate

Effective deployment at industry scale

Abstract

Embedding-based neural retrieval is a prevalent approach to address the semantic gap problem which often arises in product search on tail queries. In contrast, popular queries typically lack context and have a broad intent where additional context from users historical interaction can be helpful. In this paper, we share our novel approach to address both: the semantic gap problem followed by an end to end trained model for personalized semantic retrieval. We propose learning a unified embedding model incorporating graph, transformer and term-based embeddings end to end and share our design choices for optimal tradeoff between performance and efficiency. We share our learnings in feature engineering, hard negative sampling strategy, and application of transformer model, including a novel pre-training strategy and other tricks for improving search relevance and deploying such a model at industry scale. Our personalized retrieval model significantly improves the overall search experience, as measured by a 5.58% increase in search purchase rate and a 2.63% increase in site-wide conversion rate, aggregated across multiple A/B tests - on live traffic.