Session Context Embedding for Intent Understanding in Product Search

TL;DR

The paper tackles how to capture user intent in product search by incorporating session context into vector representations. It introduces session embedding, an augmentation of traditional query embeddings that integrates prior queries and engaged items, produced by lightweight LLMs and usable at runtime for retrieval and reranking. Training uses session-based labels derived from conversion events across a large dataset, demonstrating that broad-to-narrow query transitions in sessions significantly improve product-type classification accuracy, while narrow-to-broad transitions may not. The findings suggest that leveraging session evolution can meaningfully enhance intent understanding and that efficient LLM-based vectorization is practical for production deployment.

Abstract

It is often noted that single query-item pair relevance training in search does not capture the customer intent. User intent can be better deduced from a series of engagements (Clicks, ATCs, Orders) in a given search session. We propose a novel method for vectorizing session context for capturing and utilizing context in retrieval and rerank. In the runtime, session embedding is an alternative to query embedding, saved and updated after each request in the session, it can be used for retrieval and ranking. We outline session embedding's solution to session-based intent understanding and its architecture, the background to this line of thought in search and recommendation, detail the methodologies implemented, and finally present the results of an implementation of session embedding for query product type classification. We demonstrate improvements over strategies ignoring session context in the runtime for user intent understanding.

Figures (1)

• Figure 1: Session embedding