Feature-combination hybrid recommender systems for automated music playlist continuation

Abstract

Music recommender systems have become a key technology to support the interaction of users with the increasingly larger music catalogs of on-line music streaming services, on-line music shops, and personal devices. An important task in music recommender systems is the automated continuation of music playlists, that enables the recommendation of music streams adapting to given (possibly short) listening sessions. Previous works have shown that applying collaborative filtering to collections of curated music playlists reveals underlying playlist-song co-occurrence patterns that are useful to predict playlist continuations. However, most music collections exhibit a pronounced long-tailed distribution. The majority of songs occur only in few playlists and, as a consequence, they are poorly represented by collaborative filtering. We introduce two feature-combination hybrid recommender systems that extend collaborative filtering by integrating the collaborative information encoded in curated music playlists with any type of song feature vector representation. We conduct off-line experiments to assess the performance of the proposed systems to recover withheld playlist continuations, and we compare them to competitive pure and hybrid collaborative filtering baselines. The results of the experiments indicate that the introduced feature-combination hybrid recommender systems can more accurately predict fitting playlist continuations as a result of their improved representation of songs occurring in few playlists.

Trends in content-based recommendation

“…Finally, the paper Feature-combination hybrid recommender systems for automated music playlist continuation (Vall et al 2019) contributes to the area of music recommendation. The authors introduce two feature-combination hybrid recommender systems that combine collaborative information from curated music playlists with song features.…”

Hybrid semantic recommender system for chemical compounds in large-scale datasets

“…For the CF module, we selected two CF recommender algorithms for recommending data collected from implicit feedback, Alternating Least Squares (ALS) [ 41 ] and Bayesian Personalized Ranking (BPR) [ 7 ], both implemented in the library Fast python collaborative filtering for implicit datasets (implicit) [ 49 ]. These algorithms and the implementation in the implicit library are suitable for the type of dataset we are using and they were already used with similar datasets, i.e., recommendation datasets of implicit feedback, especially for recommending music playlists [ 50 , 51 ]. ALS and BPR are used separately in the CF module.…”

Hybrid Semantic Recommender System for Chemical Compounds in Large-Scale Datasets

“…For the CF module, we selected two CF recommender algorithms for recommending data collected from implicit feedback, Alternating Least Squares (ALS) [41] and Bayesian Personalized Ranking (BPR) [7], both implemented in the library Fast python collaborative filtering for implicit datasets (implicit) [49]. These algorithms and the implementation in the implicit library are suitable for the type of dataset we are using and they were already used with similar datasets, i.e., recommendation datasets of implicit feedback, especially for recommending music playlists [50,51]. ALS and BPR are used separately in the CF module.…”