mlsanityData to 14 Oct 2026

A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps

arXiv 2106.03819 ↗First posted 7 Jun 2021cs.IR cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Music streaming services heavily rely on recommender systems to improve their users' experience, by helping them navigate through a large musical catalog and discover new songs, albums or artists. However, recommending relevant and personalized content to new users, with few to no interactions with the catalog, is challenging. This is commonly referred to as the user cold start problem. In this applied paper, we present the system recently deployed on the music streaming service Deezer to address this problem. The solution leverages a semi-personalized recommendation strategy, based on a deep neural network architecture and on a clustering of users from heterogeneous sources of information. We extensively show the practical impact of this system and its effectiveness at predicting the future musical preferences of cold start users on Deezer, through both offline and online large-scale experiments. Besides, we publicly release our code as well as anonymized usage data from our experiments. We hope that this release of industrial resources will benefit future research on user cold start recommendation.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 20 of its 51 references that are in the map. First posted on arXiv 7 Jun 2021.

Builds on

20 of 51 references.

References · 20

  1. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  2. 2017Neural Collaborative Filteringcited by 1,111
  3. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  4. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  5. 2018Meta-Learning: A Surveycited by 256
  6. 2017Advances in Pre-Training Distributed Word Representationscited by 207
  7. 2017Deep Learning based Recommender System: A Survey and New Perspectivescited by 136
  8. 2019MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendationcited by 121
  9. 2018Billion-scale Commodity Embedding for E-commerce Recommendation in Alibabacited by 105
  10. 2017Fast Matrix Factorization for Online Recommendation with Implicit Feedbackcited by 101
  11. 2014Collaborative Deep Learning for Recommender Systemscited by 95
  12. 2021Graph Learning based Recommender Systems: A Reviewcited by 59
8 more
  1. 2019STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systemscited by 54
  2. 2017Current Challenges and Visions in Music Recommender Systems Researchcited by 42
  3. 2015Metadata Embeddings for User and Item Cold-start Recommendationscited by 29
  4. 2020Carousel Personalization in Music Streaming Apps with Contextual Banditscited by 26
  5. 2019A Degeneracy Framework for Scalable Graph Autoencoderscited by 12
  6. 2020Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Predictioncited by 6
  7. 2020Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Item Annotationcited by 5
  8. 2019Deep Latent Factor Model for Collaborative Filteringcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 7; 2024: 5; 2025: 2; 2026: 4.

21 papers.

Sort:

By area:

  1. 2023Beyond Two-Tower Matching: Learning Sparse Retrievable Cross-Interactions for Recommendationcited by 13
  2. 2021Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoderscited by 12
  3. 2022Flow Moods: Recommending Music by Moods on Deezercited by 11
  4. 2023A Scalable Framework for Automatic Playlist Continuation on Music Streaming Servicescited by 7
  5. 2021Hierarchical Latent Relation Modeling for Collaborative Metric Learningcited by 6
  6. 2023Track Mix Generation on Music Streaming Services using Transformerscited by 6
  7. 2023On the Consistency of Average Embeddings for Item Recommendationcited by 5
  8. 2024Let's Get It Started: Fostering the Discoverability of New Releases on Deezercited by 5
  9. 2024Transformers Meet ACT-R: Repeat-Aware and Sequential Listening Session Recommendationcited by 4
  10. 2025Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Samplingcited by 3
  11. 2024UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systemscited by 2
  12. 2024Do Recommender Systems Promote Local Music? A Reproducibility Study Using Music Streaming Datacited by 2
9 more
  1. 2026IDProxy: CTR Prediction with Multimodal LLMs for Cold-Start Recommendation at Xiaohongshucited by 2
  2. 2023Of Spiky SVDs and Music Recommendationcited by 1
  3. 2024From Latent to Engine Manifolds: Analyzing ImageBind's Multimodal Embedding Spacecited by 1
  4. 2026Music Playlist Captioning at Scale with Large Language Modelscited by 1
  5. 2023ALT: An Automatic System for Long Tail Scenario Modelingcited by 0
  6. 2023Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?cited by 0
  7. 2025Training chord recognition models on artificially generated audiocited by 0
  8. 2026Zero-Observation User Reactivation with Gap-Driven Dimensional Gatingcited by 0
  9. 2026Privacy in Personalized AI Is a System Property, Not Just a Model Propertycited by 0