Automatic playlist continuation using a hybrid recommender system combining features from text and audio

Ferraro, Andrés; Bogdanov, Dmitry; Yoon, Jisang; Kim, KwangSeob; Serra, Xavier

doi:http://dx.doi.org/10.1145/3267471.3267473

Automatic playlist continuation using a hybrid recommender system combining features from text and audio

Citació

Ferraro A, Bogdanov D, Yoon J, Kim K, Serra X. Automatic playlist continuation using a hybrid recommender system combining features from text and audio. In: RecSys Challenge '18. Proceedings of the ACM Recommender Systems Challenge 2018; 2018 02 Oct; Vancouver, Canada. New York: ACM; 2018. Art. 2. DOI: 10.1145/3267471.3267473

Resum

The ACM RecSys Challenge 2018 focuses on music recommendation in the context of automatic playlist continuation. In this paper, we describe our approach to the problem and the final hybrid system that was submitted to the challenge by our team Cocoplaya. This system consists in combining the recommendations produced by two different models using ranking fusion. The first model is based on Matrix Factorization and it incorporates information from tracks’ audio and playlist titles. The second model generates recommendations based on typical track co-occurrences considering their proximity in the playlists. The proposed approach is efficient and achieves a good overall performance, with our model ranked 4th on the creative track of the challenge leaderboard.