High Precision Audience Expansion via Extreme Classification in a Two-Sided Marketplace
This work addresses the location retrieval problem for Airbnb's search system, which is incremental as it builds on existing methods to enhance efficiency in a two-sided marketplace.
The paper tackles the challenge of efficiently retrieving relevant listings in Airbnb's search by replacing a deep Bayesian bandit system with a method that divides the world into 25 million uniform cells to define high-precision rectangular map cells for retrieval, resulting in improved precision in surfacing bookable listings.
Airbnb search must balance a worldwide, highly varied supply of homes with guests whose location, amenity, style, and price expectations differ widely. Meeting those expectations hinges on an efficient retrieval stage that surfaces only the listings a guest might realistically book, before resource intensive ranking models are applied to determine the best results. Unlike many recommendation engines, our system faces a distinctive challenge, location retrieval, that sits upstream of ranking and determines which geographic areas are queried in order to filter inventory to a candidate set. The preexisting approach employs a deep bayesian bandit based system to predict a rectangular retrieval bounds area that can be used for filtering. The purpose of this paper is to demonstrate the methodology, challenges, and impact of rearchitecting search to retrieve from the subset of most bookable high precision rectangular map cells defined by dividing the world into 25M uniform cells.