How can you rank product search results when you have very little data about how past shoppers have interacted with the products? Through large scale analysis of its clickstream data, Etsy is automatically discovering product attributes (things like materials, prices, or text features) which signal that a search result is particularly relevant (or irrelevant) to a given query. This attribute-level approach makes it possible to appropriately rank products in search results- even if those products are brand new and one-of-a-kind. This presentation discusses Etsy’s efforts to predict relevance in product search, in which Hadoop is a central component.
Aaron Beppu
Software Engineer
Etsy
Aaron Beppu is a software engineer focused on product search at Etsy. His recent work, built on the premise that “product search is a learning task”, seeks to use large volumes of click stream data to improve ranking in Etsy’s search results. Prior to working at Etsy, he spent 2.5 years on the search analytics team at A9, using click stream data to measure search quality and model searcher behavior for Amazon.