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