Music Recommender Performance for Beyond-Mainstream Listeners
|Number of Students||
Music recommender systems have become a central service of music streaming platforms such as Spotify or deezer. Traditionally, the recommender systems employed serve listeners of mainstream music well, while being less accurate when it comes to computing recommendations for listeners with non-mainstream taste in music. In this thesis, we aim to benchmark the performance of state-of-the-art music recommendation algorithms for beyond-mainstream music listener groups.