Score Design for Multi-Criteria Incentivization

Autor:	Kabra, Anmol, Karzand, Mina, Lechner, Tosca, Srebro, Nathan, Wang, Serena
Rok vydání:	2024
Předmět:	Computer Science - Computers and Society Computer Science - Computational Geometry Computer Science - Machine Learning
Druh dokumentu:	Working Paper
DOI:	10.4230/LIPIcs.FORC.2024.8
Popis:	We present a framework for designing scores to summarize performance metrics. Our design has two multi-criteria objectives: (1) improving on scores should improve all performance metrics, and (2) achieving pareto-optimal scores should achieve pareto-optimal metrics. We formulate our design to minimize the dimensionality of scores while satisfying the objectives. We give algorithms to design scores, which are provably minimal under mild assumptions on the structure of performance metrics. This framework draws motivation from real-world practices in hospital rating systems, where misaligned scores and performance metrics lead to unintended consequences. Comment: A condensed version of this paper appeared at Foundations of Responsible Computing (FORC) 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.06290 Zobrazit plný text záznamu View this record from Arxiv