IRAIJul 1

IntentTune: Using user demand and personalization to resolve "unknown" query intents for e-commerce search

arXiv:2607.015307.4
Predicted impact top 54% in IR · last 90 daysOriginality Incremental advance
AI Analysis

For e-commerce search systems, this addresses the problem of ambiguous queries that lack explicit attributes, improving retrieval relevance.

IntentTune resolves under-specified e-commerce queries (e.g., "watch") by inferring latent intents (gender, age, etc.) using user-specific behavioral signals. Experiments show that prior search queries outperform population-level demand patterns and static profile information for intent inference.

Understanding user intent is fundamental to delivering relevant search results in e-commerce. However, substantial fraction of real-world queries are under-specified (e.g., "watch" or "shirt"), lacking explicit attributes such as gender or age group. This ambiguity poses a significant challenge for query intent detection models in e-commerce search systems, which must accurately infer latent user intent (e.g., age, gender) to support effective downstream retrieval. We introduce IntentTune, a framework for resolving ambiguous or under-specified query intents by leveraging either (1) user-specific behavioral signals including search history, browsing activity, and profile attributes or (2) population-level demand patterns aggregated across all users. Through experiments on real-world e-commerce data, we first demonstrate that population-level demand patterns alone are insufficient to reliably infer intent in under-specified queries. We then demonstrate that user-specific behavioral signals -- particularly prior search queries -- outperform both population-level statistics and static profile information for inferring gender, age group, product category, and size intent from underspecified queries.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes