Contextually Aware E-Commerce Product Question Answering using RAG

TL;DR

This paper presents a scalable RAG-based framework for e-commerce product question answering that effectively incorporates user context and diverse product information to improve answer relevance and personalization.

Contribution

It introduces a novel end-to-end RAG framework that integrates rich contextual data and new metrics for evaluating e-commerce PQA systems.

Findings

Handles diverse query types effectively

Improves answer relevance with contextual integration

Identifies information gaps for content enhancement

Abstract

E-commerce product pages contain a mix of structured specifications, unstructured reviews, and contextual elements like personalized offers or regional variants. Although informative, this volume can lead to cognitive overload, making it difficult for users to quickly and accurately find the information they need. Existing Product Question Answering (PQA) systems often fail to utilize rich user context and diverse product information effectively. We propose a scalable, end-to-end framework for e-commerce PQA using Retrieval Augmented Generation (RAG) that deeply integrates contextual understanding. Our system leverages conversational history, user profiles, and product attributes to deliver relevant and personalized answers. It adeptly handles objective, subjective, and multi-intent queries across heterogeneous sources, while also identifying information gaps in the catalog to support ongoing content improvement. We also introduce novel metrics to measure the framework's performance which are broadly applicable for RAG system evaluations.