Contextual and Sequential User Embeddings for Large-Scale Music Recommendation
Casper Hansen, Christian Hansen, Lucas Maystre, Rishabh Mehrotra, Brian Brost, Federico Tomasi, Mounia Lalmas
User Modeling
Serving the diverse needs of millions of users requires the development of technology to not only understand user tastes and interests, but also consider contextual preferences of the users to serve them relevant, timely and inspirational recommendations. The user modeling research at Spotify entails translating users’ in-app activities into human traits, interaction models, emotional understanding modules, and situational contexts, thereby uncovering our users’ individuality. To do this, we use a multidisciplinary scientific approach at the intersection of music psychology, behavioral analysis, and machine learning. This enables us to build datasets and user interaction models to create engaging and personalized experiences for our users, in a data-driven fashion based on users’ interactions and feedback signals.
