Query as Context for Item-to-Item Recommendation

ABSTRACT Recommender Systems is one of the main machine learning applications for an e-commerce platforms such as Etsy, a two sided marketplace. A frequent usage of such system is for item-to-item recommendations that show similar items (also referred as listings) based on the listing a user is currently viewing. Item-to-item recommendations typically take into account information that are only associated with the target listing and other listings in the inventory. However, other contextual information such as user intents, queries and seasonality, are often not taken into account. In this talk, we will present two approaches we developed to utilize additional contextual information in the form of queries in generating item-to-item recommendations. Moreover, we will present our journey in migrating Etsy’s rankers from linear to non-linear models. Additionally, we propose new metrics to evaluate candidate sets that accesses diversity and price spread, while not compromising relevance. The proposed metrics can also be used beyond the current application. Our proposed candidate set generation approach outperforms the model in production as well as yielding significant lift in conversion rate and other engagement metrics as indicated by several A/B tests.