Calibrated Recommendations with Contextual Bandits
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912574106238976 |
|---|---|
| author | Feijer, Diego Abdollahpouri, Himan Gupta, Sanket Clare, Alexander Wen, Yuxiao Wasson, Todd Dimakopoulou, Maria Nazari, Zahra Kretschman, Kyle Lalmas, Mounia |
| author_facet | Feijer, Diego Abdollahpouri, Himan Gupta, Sanket Clare, Alexander Wen, Yuxiao Wasson, Todd Dimakopoulou, Maria Nazari, Zahra Kretschman, Kyle Lalmas, Mounia |
| contents | Spotify's Home page features a variety of content types, including music, podcasts, and audiobooks. However, historical data is heavily skewed toward music, making it challenging to deliver a balanced and personalized content mix. Moreover, users' preference towards different content types may vary depending on the time of day, the day of week, or even the device they use. We propose a calibration method that leverages contextual bandits to dynamically learn each user's optimal content type distribution based on their context and preferences. Unlike traditional calibration methods that rely on historical averages, our approach boosts engagement by adapting to how users interests in different content types varies across contexts. Both offline and online results demonstrate improved precision and user engagement with the Spotify Home page, in particular with under-represented content types such as podcasts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05460 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Calibrated Recommendations with Contextual Bandits Feijer, Diego Abdollahpouri, Himan Gupta, Sanket Clare, Alexander Wen, Yuxiao Wasson, Todd Dimakopoulou, Maria Nazari, Zahra Kretschman, Kyle Lalmas, Mounia Machine Learning Information Retrieval Spotify's Home page features a variety of content types, including music, podcasts, and audiobooks. However, historical data is heavily skewed toward music, making it challenging to deliver a balanced and personalized content mix. Moreover, users' preference towards different content types may vary depending on the time of day, the day of week, or even the device they use. We propose a calibration method that leverages contextual bandits to dynamically learn each user's optimal content type distribution based on their context and preferences. Unlike traditional calibration methods that rely on historical averages, our approach boosts engagement by adapting to how users interests in different content types varies across contexts. Both offline and online results demonstrate improved precision and user engagement with the Spotify Home page, in particular with under-represented content types such as podcasts. |
| title | Calibrated Recommendations with Contextual Bandits |
| topic | Machine Learning Information Retrieval |
| url | https://arxiv.org/abs/2509.05460 |