Bridging the Gap Between Information Seeking and Product Search Systems: Q&A Recommendation for E-commerce

TL;DR

Bridging the gap between information seeking and product search, the paper proposes Q&A pair recommendations within e-commerce product search to support purchase decisions. It advocates an LLM-driven framework that generates context-aware questions and answers using inputs from queries, SERP, and product detail pages, with personalization considerations. The work details Q&A requirements, generation methods (including retrieval-augmented generation), evaluation and quality-control strategies, and engagement-optimization techniques, while acknowledging production challenges such as latency and cost. Overall, the approach aims to streamline the shopping process by integrating conversational QA into the product discovery journey, enabling faster, more informed purchases.

Abstract

Consumers on a shopping mission often leverage both product search and information seeking systems, such as web search engines and Question Answering (QA) systems, in an iterative process to improve their understanding of available products and reach a purchase decision. While product search is useful for shoppers to find the actual products meeting their requirements in the catalog, information seeking systems can be utilized to answer any questions they may have to refine those requirements. The recent success of Large Language Models (LLMs) has opened up an opportunity to bridge the gap between the two tasks to help customers achieve their goals quickly and effectively by integrating conversational QA within product search. In this paper, we propose to recommend users Question-Answer (Q&A) pairs that are relevant to their product search and can help them make a purchase decision. We discuss the different aspects of the problem including the requirements and characteristics of the Q&A pairs, their generation, and the optimization of the Q&A recommendation task. We highlight the challenges, open problems, and suggested solutions to encourage future research in this emerging area.

Figures (2)

• Figure 1: The current online shopping process. Users are switching between information seeking systems and product search to reach a purchase decision. The dashed arrow represents our envisioned approach to bridge the gap between the two systems.
• Figure 2: An illustration of the suggested questions interface for the auto-complete stage.