Dataset Open Access

Datasets from the RecSys 2020 article "Carousel Personalization in Music Streaming Apps with Contextual Bandits"

Bendada, Walid; Salha, Guillaume; Bontempelli, Théo

We publicly release the anonymized user_features.csv and playlist_features.csv datasets, from the music streaming platform Deezer, as described in the article "Carousel Personalization in Music Streaming Apps with Contextual Bandits" published in the proceedings of the 14th ACM Conference on Recommender Systems (RecSys 2020). The paper is available here.

These datasets are used in the GitHub repository deezer/carousel_bandits to reproduce experiments from the article.

Please cite our paper if you use our code or data in your work.

Files (1.8 GB)
Name Size
playlist_features.csv
md5:5b8f1e07a91186e5d7e9546f9fd4bb66
1.8 MB Download
user_features.csv
md5:d90db984400bca94c2b74566e4625a63
1.8 GB Download
204
74
views
downloads
All versions This version
Views 204204
Downloads 7474
Data volume 81.2 GB81.2 GB
Unique views 178178
Unique downloads 4646

Share

Cite as