Abstract

Multi-sided marketplaces have witnessed an explosive growth by facilitating efficient interactions between multiple stakeholders, including e.g. buyers and retailers (Amazon), guests and hosts (AirBnb), riders and drivers (Uber), and listeners and artists (Spotify). A large number of such platforms rely on machine learning powered matching engines connecting consumers with suppliers by acting as a central platform, thereby finding the right fit and efficiently mediating economic transactions between the two sides.

In this talk, we begin by describing a contextual bandit model developed for serving explainable music recommendations to users and showcase the need for explicitly considering supplier-centric objectives during optimization. We demonstrate how enhanced user and content understanding helps us in developing better models to power multi-stakeholder marketplaces. Towards the end, we highlight key NLP challenges faced when developing such systems to power large scale marketplaces.

Bio: Rishabh Mehrotra is a Senior Research Scientist at Spotify Research in London. He obtained his PhD in the field of Machine Learning and Information Retrieval from University College London where he was partially supported by a Google Research Award. His current research focuses on marketplace ML and bandit based recommendations. Some of his recent work has been published at top conferences including WWW , SIGIR, NAACL , CIKM, RecSys and WSDM . He has co-taught a number of tutorials at leading conferences & multiple courses at summer schools.