Let's Get It Started: Fostering the Discoverability of New Releases on Deezer
This addresses the challenge of helping users find new music on streaming platforms, though it is incremental as it builds on existing recommendation techniques.
The paper tackled the problem of improving discoverability of new music releases on Deezer by shifting from editorial to personalized recommendations using cold start embeddings and contextual bandits, resulting in enhanced recommendation quality and exposure as validated by online experiments.
This paper presents our recent initiatives to foster the discoverability of new releases on the music streaming service Deezer. After introducing our search and recommendation features dedicated to new releases, we outline our shift from editorial to personalized release suggestions using cold start embeddings and contextual bandits. Backed by online experiments, we discuss the advantages of this shift in terms of recommendation quality and exposure of new releases on the service.