AI Guided Accelerator For Search Experience
Jayanth Yetukuri, Mehran Elyasi, Samarth Agrawal, Aritra Mandal, Rui Kong, Harish Vempati, Ishita Khan
TL;DR
This work addresses the challenge of evolving user intent in e-commerce search by focusing on transitional queries that occur along the shopping journey. It combines structured query trajectory mining from large-scale logs with an open-source LLM-based alternator to generate diverse, intent-preserving converging queries, enabling richer SRP carousels and related searches. An intent-consistency filter ensures transitions preserve the original source intent, while the LLM expands the candidate space to improve discovery and engagement. Empirical results show measurable gains in CTR and conversions over the production Related Searches module, demonstrating the practical potential of integrating behavioral mining with generative query expansion for scalable, intent-aware search experiences.
Abstract
Effective query reformulation is pivotal in narrowing the gap between a user's exploratory search behavior and the identification of relevant products in e-commerce environments. While traditional approaches predominantly model query rewrites as isolated pairs, they often fail to capture the sequential and transitional dynamics inherent in real-world user behavior. In this work, we propose a novel framework that explicitly models transitional queries--intermediate reformulations occurring during the user's journey toward their final purchase intent. By mining structured query trajectories from eBay's large-scale user interaction logs, we reconstruct query sequences that reflect shifts in intent while preserving semantic coherence. This approach allows us to model a user's shopping funnel, where mid-journey transitions reflect exploratory behavior and intent refinement. Furthermore, we incorporate generative Large Language Models (LLMs) to produce semantically diverse and intent-preserving alternative queries, extending beyond what can be derived through collaborative filtering alone. These reformulations can be leveraged to populate Related Searches or to power intent-clustered carousels on the search results page, enhancing both discovery and engagement. Our contributions include (i) the formal identification and modeling of transitional queries, (ii) the introduction of a structured query sequence mining pipeline for intent flow understanding, and (iii) the application of LLMs for scalable, intent-aware query expansion. Empirical evaluation demonstrates measurable gains in conversion and engagement metrics compared to the existing Related Searches module, validating the effectiveness of our approach in real-world e-commerce settings.