A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps

TL;DR

This paper presents a semi-personalized recommendation system deployed on Deezer to address the user cold start problem in music streaming, leveraging deep neural networks and user clustering for improved predictions.

Contribution

It introduces a novel semi-personalized approach combining deep learning and user clustering, specifically designed for cold start scenarios in music streaming services.

Findings

Effective at predicting new users' preferences in Deezer

Outperforms baseline methods in offline and online tests

Code and data publicly released for research use

Abstract

Music streaming services heavily rely on recommender systems to improve their users' experience, by helping them navigate through a large musical catalog and discover new songs, albums or artists. However, recommending relevant and personalized content to new users, with few to no interactions with the catalog, is challenging. This is commonly referred to as the user cold start problem. In this applied paper, we present the system recently deployed on the music streaming service Deezer to address this problem. The solution leverages a semi-personalized recommendation strategy, based on a deep neural network architecture and on a clustering of users from heterogeneous sources of information. We extensively show the practical impact of this system and its effectiveness at predicting the future musical preferences of cold start users on Deezer, through both offline and online large-scale experiments. Besides, we publicly release our code as well as anonymized usage data from our experiments. We hope that this release of industrial resources will benefit future research on user cold start recommendation.