# Contextual Scalarisation Thompson Sampling for multi-objective decisions in public media

arXiv: https://arxiv.org/abs/2605.31291 · HTML: https://mlsanity.com/paper/2605.31291/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 28 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 7 of 7)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Contextual-Bandit Based Personalized Recommendation with Time-Varying User Interests](https://mlsanity.com/paper/2003.00359/) (2020)
- [Scalable Neural Contextual Bandit for Recommender Systems](https://mlsanity.com/paper/2306.14834/) (2023)
- [HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation](https://mlsanity.com/paper/2308.08497/) (2023)
- [Pareto-based Multi-Objective Recommender System with Forgetting Curve](https://mlsanity.com/paper/2312.16868/) (2023)
- [Utility-Based Context-Aware Multi-Agent Recommendation System for Energy Efficiency in Residential Buildings](https://mlsanity.com/paper/2205.02704/) (2022)

## Abstract (arXiv)

Recommender systems may operate under multiple, competing objectives. For example, audience reach, cultural values, public service mandate, and operational constraints must be balanced in editorial decisions of public service media. Existing approaches relying on fixed combinations of objectives or Pareto-based optimisation do not adapt to changing priorities across situations. In this paper, we propose Contextual Scalarisation Thompson Sampler (CSTS), a multi-objective contextual bandit method that learns to weight objectives as a function of the observed context. We evaluate CSTS on real programming data from Radio T'el'evision Suisse, the Swiss national broadcaster, showing improved contextual relevance and better alignment with expert curation practices compared to fixed weight and standard contextual bandit approaches.