Dataset Open Access

Datasets from the KDD 2021 article "A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps"

Léa Briand; Guillaume Salha-Galvan; Walid Bendada; Mathieu Morlon; Viet-Anh Tran

We publicly release the anonymized song_embeddings.parquet  user_embeddings.parquet  user_features_test.parquet  user_features_train.parquet  user_features_validation.parquet datasets, with each of the TT-SVD or UT-ALS versions of embeddings, from the music streaming platform Deezer, as described in the article "A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps" published in the proceedings of the 27TH ACM SIGKDD conference on knowledge discovery and data mining (KDD 2021). The paper is available here.

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

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

Files (3.5 GB)
Name Size
song_embeddings.parquet
md5:b430c50686c0e2dfb4c0aadbc916f636
129.7 MB Download
user_embeddings.parquet
md5:c5f8843ea95bbedd1c36b64da55b8afd
427.2 MB Download
user_features_test_mf.parquet
md5:825213114a7ba070af520cd584619264
161.4 MB Download
user_features_test_svd.parquet
md5:c192166a5e4b4a4fd742e6ec03415785
82.5 MB Download
user_features_train_mf.parquet
md5:b71349d6c756bb929e3a7803688df7d0
1.4 GB Download
user_features_train_svd.parquet
md5:59a1f3e85e8cfd6903491741386807fd
733.9 MB Download
user_features_validation_mf.parquet
md5:bb1965628b4054526c2c7c6df83b26bd
320.1 MB Download
user_features_validation_svd.parquet
md5:6a84bea5d9f3332cefee0fe3ac0c7f9d
163.4 MB Download
85
81
views
downloads
All versions This version
Views 8585
Downloads 8181
Data volume 31.5 GB31.5 GB
Unique views 7474
Unique downloads 1717

Share

Cite as