Machine Learning Approaches to Hybrid Music Recommender Systems
This work addresses the problem of improving music recommendation for users of streaming services and collections, but it appears incremental as it surveys and builds on existing hybrid approaches.
The paper tackles the challenge of music recommendation by proposing hybrid systems that integrate various techniques to address the cold-start problem for new items and promote discovery of non-popular music, with a focus on analyzing playlist continuation through characteristics, song features, and playlist-song relationships.
Music recommender systems have become a key technology supporting the access to increasingly larger music catalogs in on-line music streaming services, on-line music shops, and private collections. The interaction of users with large music catalogs is a complex phenomenon researched from different disciplines. We survey our works investigating the machine learning and data mining aspects of hybrid music recommender systems (i.e., systems that integrate different recommendation techniques). We proposed hybrid music recommender systems based solely on data and robust to the so-called "cold-start problem" for new music items, favoring the discovery of relevant but non-popular music. We thoroughly studied the specific task of music playlist continuation, by analyzing fundamental playlist characteristics, song feature representations, and the relationship between playlists and the songs therein.