AI TraceTrace Foundation, Inc.
Recommendation SystemConsumer FacingVerified

Reviewed and published by trentmaziarz, March 18, 2026. Discovered and drafted by our automated research pipeline.

Everything a user sees on Spotify's home screen — playlists, podcasts, albums, shortcuts — is ranked and ordered by AI based on that individual's listening patterns and predicted preferences.

Details

Uses a two-stage pipeline (candidate generation + ranking) and a multi-armed bandit framework balancing familiar and new content. Runs on TFX, Kubeflow, and Google Cloud. Models retrain weekly. Led by Tony Jebara (formerly Netflix). The system optimizes for long-term satisfaction, not just clicks.

Products affected

Spotify (Free and Premium)

Sources & Evidence

Other practices by Spotify

Have evidence about Spotify's AI practices? Submit a report.

Report a Sighting →