Evaluating Recommender System Algorithms for Generating Local Music Playlists
This addresses the challenge of generating personalized playlists for obscure local artists with little user data, which is an incremental improvement in music recommendation for niche listeners.
The paper tackled the cold-start problem in recommending local music by comparing three standard algorithms on the Million Playlist Dataset, finding that the neighborhood-based approach (IIN) performed best for long-tail local artists despite matrix factorization methods typically excelling in large tasks.
We explore the task of local music recommendation: provide listeners with personalized playlists of relevant tracks by artists who play most of their live events within a small geographic area. Most local artists tend to be obscure, long-tail artists and generally have little or no available user preference data associated with them. This creates a cold-start problem for collaborative filtering-based recommendation algorithms that depend on large amounts of such information to make accurate recommendations. In this paper, we compare the performance of three standard recommender system algorithms (Item-Item Neighborhood (IIN), Alternating Least Squares for Implicit Feedback (ALS), and Bayesian Personalized Ranking (BPR)) on the task of local music recommendation using the Million Playlist Dataset. To do this, we modify the standard evaluation procedure such that the algorithms only rank tracks by local artists for each of the eight different cities. Despite the fact that techniques based on matrix factorization (ALS, BPR) typically perform best on large recommendation tasks, we find that the neighborhood-based approach (IIN) performs best for long-tail local music recommendation.