Shifting Consumption towards Diverse content via Reinforcement Learning - Spotify Research : Spotify Research
Algorithmically generated recommendations power and shape the bulk of music consumption on music streaming platforms. The ability to shift consumption towards less popular content and towards content different from user’s typical historic tastes not only affords the platform ways of handling issues
Shifting Consumption towards Diverse content via Reinforcement Learning | Spotify Research Shifting Consumption towards Diverse content via Reinforcement Learning Algorithmically generated recommendations power and shape the bulk of music consumption on music streaming platforms. The ability to shift consumption towards less popular content and towards content different from user’s typical historic tastes not only affords the platform ways of handling issues such as filter bubbles and popularity bias, but also contributes to maintaining a healthy and sustainable consumption patterns necessary
related reading
- Algorithmic Effects on the Diversity of Consumption on Spotify | Spotify Researchresearch.atspotify.com
- Spotify Reinforcement Learning Recommendation Systemsophieyanzhao.github.io
- [2305.18290] Direct Preference Optimization: Your Language Model is Secretly a Reward Modelarxiv.org
- The Inner Workings of Spotify’s AI-Powered Music Recommendations: How Spotify Shapes Your Playlist | by Nima Torabi | Beyond the Build | Mediummedium.com
- Reconciling the accuracy-diversity trade-off in recommendationsarxiv.org
- How Spotify’s AI-Driven Recommendations Work | WSJ Tech Behindyoutube.com
- Algorithmic Symphonies: How Spotify Strikes the Right Chord – Illumin Magazine - USC Viterbi School of Engineeringillumin.usc.edu
- Improving Composer through real-time RL · Cursorcursor.com
- Publications | Spotify Researchresearch.atspotify.com
- Probabilistic Matrix Factorization for Music Recommendationcs229.stanford.edu
- Flow Matching Policy Gradientsflowreinforce.github.io
- [1904.06813] Personalized Re-ranking for Recommendationarxiv.org