Intent-Aware Neural Query Reformulation for Behavior-Aligned Product Search

2025-07-29

AI Summary

To address query–purchase intent mismatch in e-commerce search, this paper proposes an intent-aware query rewriting framework. First, it integrates explicit user behaviors (e.g., clicks, add-to-cart, purchases) with implicit signals (e.g., dwell time, scroll depth) and applies sequence mining to construct a fine-grained, intent-rich dataset. Second, it designs a supervised neural query rewriting model that enables semantic transition from lexical matching to intent alignment. This work is the first to systematically jointly model heterogeneous, multi-source behavioral signals for deep purchase intent representation and to establish an end-to-end behavior-aligned data pipeline. Experiments across multiple product categories demonstrate significant improvements: +12.7% in precision@10 and +8.3% in click-through rate (CTR), validating the dual benefits of intent-driven rewriting on both retrieval quality and key business metrics.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Understanding and modeling buyer intent is a foundational challenge in optimizing search query reformulation within the dynamic landscape of e-commerce search systems. This work introduces a robust data pipeline designed to mine and analyze large-scale buyer query logs, with a focus on extracting fine-grained intent signals from both explicit interactions and implicit behavioral cues. Leveraging advanced sequence mining techniques and supervised learning models, the pipeline systematically captures patterns indicative of latent purchase intent, enabling the construction of a high-fidelity, intent-rich dataset. The proposed framework facilitates the development of adaptive query rewrite strategies by grounding reformulations in inferred user intent rather than surface-level lexical signals. This alignment between query rewriting and underlying user objectives enhances both retrieval relevance and downstream engagement metrics. Empirical evaluations across multiple product verticals demonstrate measurable gains in precision-oriented relevance metrics, underscoring the efficacy of intent-aware reformulation. Our findings highlight the value of intent-centric modeling in bridging the gap between sparse user inputs and complex product discovery goals, and establish a scalable foundation for future research in user-aligned neural retrieval and ranking systems.

Problem

• Mining buyer intent from query logs and behavior
• Developing intent-aware query rewrite strategies
• Improving retrieval relevance and engagement metrics

Innovation

• Mining large-scale buyer query logs
• Leveraging sequence mining and supervised learning
• Intent-aware adaptive query rewrite strategies