# Calibrated Recommendations with Contextual Bandits

arXiv: https://arxiv.org/abs/2509.05460 · HTML: https://mlsanity.com/paper/2509.05460/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 32 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 5 of 5)

- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [User-centered Evaluation of Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2103.06364/) (2021)
- [Measuring the Business Value of Recommender Systems](https://mlsanity.com/paper/1908.08328/) (2019)
- [Imitation-Regularized Offline Learning](https://mlsanity.com/paper/1901.04723/) (2019)
- [Ranking Across Different Content Types: The Robust Beauty of Multinomial Blending](https://mlsanity.com/paper/2408.09168/) (2024)

## Built on by (most cited first, 3 of 3)

- [Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity](https://mlsanity.com/paper/2605.20269/) (2026)
- [Bandit Simulation for Average Reward Inference](https://mlsanity.com/paper/2606.00913/) (2026)
- [Bandits for Efficient Experimentation: Adapting to Control Group, Preferences, and Context Drifts](https://mlsanity.com/paper/2606.09802/) (2026)

## Abstract (arXiv)

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.