Research map / Learning theory and algorithms / Submodular and game algorithms
Taming the Matthew Effect in Online Markets with Social Influence
Franco Berbeglia, Pascal Van Hentenryck
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 |
|---|---|---|---|
| replace quality ranking with randomized segmentation protocol (RSP) | social influence market · MusicLab simulation (50 runs, 2M customers) | inequality measure: 1 -> 0.45 | Improved |
| RSP vs quality ranking, third quartile purchases product 1 | social influence market · MusicLab simulation (50 runs, 2M customers) | purchases: 13 105 -> 8 105 | Improved |
| RSP vs quality ranking, third quartile purchases product 2 | social influence market · MusicLab simulation (50 runs, 2M customers) | purchases: 11 105 -> 6 105 | Improved |
| RSP splits market into worlds | social influence market · MusicLab simulation (50 runs, 2M customers) | aggregate purchases | Hurt |
| RSP with 10 worlds, more customers | social influence market · MusicLab simulation (50 runs, 2M customers) | purchase loss ratio | Improved |
| increase number of worlds | RSP · MusicLab data | purchase loss ratio | Hurt |
| RSP vs quality ranking, spread of purchases | social influence market · MusicLab simulation (50 runs, 2M customers) | variance of total purchases | Improved |
| RSP on aggregate purchases of top 3 products | social influence market · MusicLab simulation (50 runs, 2M customers) | variance of aggregated purchases | Hurt |
Closest papers by meaning
- Policy Design for Two-sided Platforms with Participation Dynamics (ICML 2025 · similarity 0.80)
- Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis (ICLR 2025 · similarity 0.80)
- Homogeneous Algorithms Can Reduce Competition in Personalized Pricing (NeurIPS 2025 · similarity 0.80)
- Online Learning in Betting Markets: Profit versus Prediction (ICML 2024 · similarity 0.80)
- Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Platforms? (ICML 2025 · similarity 0.80)
- TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets (NeurIPS 2025 · similarity 0.79)
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.
