Contextual Scalarisation Thompson Sampling for multi-objective decisions in public media
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918531502702592 |
|---|---|
| author | Maëtz, Théo Guillet, Luc Cavallaro, Andrea |
| author_facet | Maëtz, Théo Guillet, Luc Cavallaro, Andrea |
| contents | 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 Télévision 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_31291 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Contextual Scalarisation Thompson Sampling for multi-objective decisions in public media Maëtz, Théo Guillet, Luc Cavallaro, Andrea Information Retrieval Machine Learning 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 Télévision 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. |
| title | Contextual Scalarisation Thompson Sampling for multi-objective decisions in public media |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2605.31291 |