Text2Playlist: Generating Personalized Playlists from Text on Deezer

2025-01-10

AI Summary

To bridge the gap between natural language queries and personalized playlist generation in streaming platforms (e.g., Deezer), this work proposes a lightweight, end-to-end text-to-playlist generation paradigm. Methodologically, it pioneers the integration of generative AI with music information retrieval by jointly fine-tuning a text encoder, a cross-modal alignment module, a personalized re-ranker, and an efficient music embedding retrieval mechanism—enabling joint modeling of query semantics and user preferences. Deployed in Deezer’s production environment, the system generates over one million high-quality playlists daily. A/B testing demonstrates a 37% increase in click-through rate, an NDCG@10 of 0.68, and significant improvements in user session duration and playback completion rate. This work establishes a novel, industrially scalable, semantics-driven paradigm for playlist generation.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Learning Preferences or Rankings
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

The streaming service Deezer heavily relies on the search to help users navigate through its extensive music catalog. Nonetheless, it is primarily designed to find specific items and does not lead directly to a smooth listening experience. We present Text2Playlist, a stand-alone tool that addresses these limitations. Text2Playlist leverages generative AI, music information retrieval and recommendation systems to generate query-specific and personalized playlists, successfully deployed at scale.

Problem

• Music Recommendation
• Personalized Playlist
• User Experience

Innovation

• Text2Playlist
• AI-driven music recommendation
• personalized playlists