Spotify separates personalization and experimentation into distinct tech stacks rather than combining them. Personalization systems (recommendation engines, contextual bandits, ML models) live in the ML platform for low-latency inference and rich feature access, while experimentation tools evaluate these systems through A/B

10m read time From engineering.atspotify.com
Post cover image
Table of contents
IntroductionWhat is personalization?The overlap between personalization and experimentationWhy we separate experimentation and personalization at SpotifyThe one-dimensional focus of multi-armed banditsHow we run personalization experiments efficientlyWrapping up

Sort: