Learning Fast - Home Experimentation and Open Research at Spotify

Explore Spotify's innovative approach to personalization and machine learning in this 28-minute conference talk. Discover how the world's leading music streaming service leverages ML technologies to create unique user experiences, from personalized playlists to concert recommendations. Gain insights into Spotify's Home screen personalization techniques, rapid experimentation methods, and infrastructure for evaluating ML models. Learn about the Recommended Tracks feature for playlist creation and the results of the RecSys Challenge 2018, an open data science initiative promoting automatic playlist continuation research. Understand how Spotify balances rapid experimentation with fostering a culture of machine learning research both internally and within the broader community.