Timezone: »
We study the problem of optimizing recommender systems for outcomes that realize over several weeks or months. Successfully addressing this problem requires overcoming difficult statistical and organizational challenges. We begin by drawing on reinforcement learning to formulate a comprehensive model of users' recurring relationship with a recommender system. We then identify a few key assumptions that lead to simple, testable recommender system prototypes that explicitly optimize for the long-term. We apply our approach to a podcast recommender system at a large online audio streaming service, and we demonstrate that purposefully optimizing for long-term outcomes can lead to substantial performance gains over approaches optimizing for short-term proxies.
Author Information
Lucas Maystre (Spotify)
Daniel Russo (Columbia)
Yu Zhao (Spotify)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 : Optimizing Audio Recommendations for the Long-Term »
Dates n/a. Room
More from the Same Authors
-
2022 Poster: Temporally-Consistent Survival Analysis »
Lucas Maystre · Daniel Russo