Query Attribute Recommendation at Amazon Search

Abstract

Query understanding models extract attributes from search queries, like color, product type, brand, etc. Search engines rely on these attributes for ranking, advertising, and recommendation, etc. However, product search queries are usually short, three or four words on average. This information shortage limits the search engine’s power to provide high-quality services. In this talk, we would like to share our year-long journey in solving the information shortage problem and introduce an end-to-end system for attribute recommendation at Amazon Search. We showcase how the system works and how the system contributes to the long-term user experience through offline and online experiments at Amazon Search. We hope this talk can inspire more follow-up works in understanding and improving attribute recommendations in product search.