Music, the window into your soul
summary
Spotify uses streaming counts and session signals plus machine learning to infer concrete life details and tune recommendations: models detect infers new parent from listening patterns, flagging that a child causes 792 plays of "Wheels on the Bus" (Wheels on the Bus played 792 times) and shifting suggestions away from adult-centric picks. The company combines machine learning models (collaborative filtering plus audio and metadata features), deploys them into personalization pipelines, and measures lift through experiment-driven engagement metrics.
AI-written summary · about
chapters (4)
- 0:00Start
- 0:10Who Are Your Favorite Artists
- 1:24Top Three Most Stream Artists
- 2:11Can Anyone Guess Who Is the Most Stream Artist on My Spotify
related talks
05mData science and streaming music - Interview with Jonathan Gosier
28mLearning Fast: Home Experimentation and Open Research at Spotify
40mPowering Spotify's Audio Personalization Platform
29mHow Spotify Does ML At Scale
34mBuilding a Large Music Recommender Leveraging AI, Deep Learning and Human Expertise
13mRevolutionizing the Music Industry with Data Science
59mClosing Keynote: Paul Lamere
10mLillian Carrasquillo, Spotify | Stanford Women in Data Science (WiDS) Conference 2020