AI Paper Atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?

Fan Yao, Chuanhao Li, Karthik Abinav Sankararaman, Yiming Liao, Yan Zhu, Qifan Wang, Hongning Wang, Haifeng Xu

NeurIPS 2023 · Learning theory and algorithms › Submodular and game algorithms · approach: Matching markets and welfare

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 changedWhereMeasuredEffect
Replace a merit-based monotone reward mechanism with a BRMContent creator competition · Synthetic dataset, G₁ and G₂social welfareImproved
Replace a merit-based monotone reward mechanism with a BRMContent creator competition · MovieLens-1m, G₁ and G₂social welfareImproved
Use BRCM_opt instead of BRCM* (ablation)BRCM · Synthetic dataset, G₁social welfareImproved
Use BRCM_opt instead of BRCM* (ablation)BRCM · Synthetic dataset, G₂social welfareHurt
Use BRCM₁ with parameters [1, 1/2, 1/3, 1/4, 1/5, 0, …, 0] instead of a monotone reward baseline (ablation)Content creator competition · Synthetic dataset, G₁social welfareImproved
Use BRCM mechanisms rather than M³ mechanismsContent creator competition · Synthetic dataset, G₁average utility for minority and niche groupsImproved
Add creator production costs (ablation)BRCM versus M³ · Synthetic dataset, G₂ versus G₁social welfare advantage of BRCM over M³Hurt
Add creator production costs (ablation)BRCM versus M³ · MovieLens-1m, G₂ versus G₁social welfare advantage of BRCM over M³Hurt
Replace BRCM* with BRCM_opt (ablation)BRCM · MovieLens-1m, G₁ and G₂social welfareNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy