Research map / Learning theory and algorithms / Submodular and game algorithms
A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers
Omer Ben-Porat, Moshe Tennenholtz
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Allocate display probabilities using the Shapley value of the induced satisfaction game | Recommendation games · General recommendation games | PNE existence | Improved |
| Use the Shapley mediator rather than a complete display rule | Recommendation systems with strategic providers · General recommendation games | joint fairness and stability | Improved |
| Use the Shapley mediator | Recommendation games · General recommendation games | Price of Anarchy: ≤ (2N-1)/N | Improved |
| Use the Shapley mediator when plain content has utility 1 | Recommendation games · Optimal plain content | User Price of Anarchy: ≤ 4; 1.76 | Mixed |
| Allow strategic providers under the Shapley mediator with zero utility for plain content | Recommendation games · Zero plain-content utility | User Price of Anarchy | Hurt |
| Use the Shapley mediator instead of TOP | Example recommendation game · Example equilibrium | user utility: 2 -> 2.145 | Improved |
| Use TOP or BTL instead of the Shapley mediator | Recommendation games · General recommendation games | stability | Hurt |
| Use NONE or RAND instead of the Shapley mediator | Recommendation games · General recommendation games | fairness | Hurt |
| Use NONE when plain content has utility 1 | Recommendation games · Optimal plain content | User Price of Anarchy: UPoA_NONE=1 | Improved |
Closest papers by meaning
- Learning to Recommend in Unknown Games (NeurIPS 2026 · similarity 0.86)
- Recommender Ecosystems: A Mechanism Design Perspective on Holistic Modeling and Optimization (AAAI 2024 · similarity 0.84)
- On the Power of Strategic Corpus Enrichment in Content Creation Games (AAAI 2025 · similarity 0.84)
- User-item fairness tradeoffs in recommendations (NeurIPS 2024 · similarity 0.83)
- Interpolating Item and User Fairness in Multi-Sided Recommendations (NeurIPS 2024 · similarity 0.83)
- Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Platforms? (ICML 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
