A Transformer-based Embedding Model for Personalized Product Search

TL;DR

This paper introduces a transformer-based embedding model (TEM) that dynamically adjusts personalization influence in product search by encoding user query and purchase history, leading to improved retrieval performance.

Contribution

The paper presents a novel transformer-based model for personalized product search that overcomes limitations of existing methods by dynamically controlling personalization effects.

Findings

TEM outperforms state-of-the-art models significantly.

Dynamic personalization improves search relevance.

Interactions between items are effectively modeled.

Abstract

Product search is an important way for people to browse and purchase items on E-commerce platforms. While customers tend to make choices based on their personal tastes and preferences, analysis of commercial product search logs has shown that personalization does not always improve product search quality. Most existing product search techniques, however, conduct undifferentiated personalization across search sessions. They either use a fixed coefficient to control the influence of personalization or let personalization take effect all the time with an attention mechanism. The only notable exception is the recently proposed zero-attention model (ZAM) that can adaptively adjust the effect of personalization by allowing the query to attend to a zero vector. Nonetheless, in ZAM, personalization can act at most as equally important as the query and the representations of items are static across the collection regardless of the items co-occurring in the user's historical purchases. Aware of these limitations, we propose a transformer-based embedding model (TEM) for personalized product search, which could dynamically control the influence of personalization by encoding the sequence of query and user's purchase history with a transformer architecture. Personalization could have a dominant impact when necessary and interactions between items can be taken into consideration when computing attention weights. Experimental results show that TEM outperforms state-of-the-art personalization product retrieval models significantly.