Session Context Embedding for Intent Understanding in Product Search

TL;DR

This paper introduces a session embedding method that captures user intent from multiple interactions within a search session, improving product search relevance and ranking accuracy.

Contribution

It presents a novel session embedding approach that dynamically updates with user interactions, enhancing intent understanding beyond single query-item relevance.

Findings

Improved product type classification accuracy

Enhanced retrieval and ranking performance

Demonstrated benefits over session-agnostic strategies

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.