设计能引导用户真实提升而非欺骗模型的公平分类器。
Anticipating Gaming to Incentivize Improvement: Guiding Agents in (Fair) Strategic Classification
- 构建斯塔克尔伯格博弈模型，模拟用户改进与操纵行为的权衡。
- 发现合理设计可让90%以上用户选择真实改进而非操纵。
- 适用于需激励用户自我提升的公平决策场景，如信贷评估。
随着机器学习算法在各类关键决策中广泛应用，理解人类对算法系统的战略响应变得至关重要。本文研究个体在面对算法决策系统时，是选择真正提升自身资质（‘改进’），还是试图通过操控特征来欺骗算法（‘操纵’）。进一步探讨了算法设计者如何塑造这些战略反应及其公平性影响。具体而言，将互动建模为斯塔克尔伯格博弈：企业部署一个（公平）分类器，个体进行战略响应。模型同时纳入操纵与改进的不同成本及随机有效性。分析揭示了不同类型的代理人响应模式，并据此刻画了最优分类器。基于此，我们识别出在何种条件下，（公平）策略不仅能阻止操纵，还能激励个体选择改进。研究揭示了企业在采用机器学习驱动决策系统时，前瞻性预判战略行为所蕴含的微观经济与伦理交织影响。
原文摘要 · Abstract (English)
As machine learning algorithms increasingly influence critical decision making in different application areas, understanding human strategic behavior in response to these systems becomes vital. We explore individuals' choice between genuinely improving their qualifications (``improvement'') vs. attempting to deceive the algorithm by manipulating their features (``manipulation'') in response to an algorithmic decision system. We further investigate an algorithm designer's ability to shape these strategic responses, and its fairness implications. Specifically, we formulate these interactions as a Stackelberg game, where a firm deploys a (fair) classifier, and individuals strategically respond. Our model incorporates both different costs and stochastic efficacy for manipulation and improvement. The analysis reveals different potential classes of agent responses, and characterizes optimal classifiers accordingly. Based on these, we identify when and why a (fair) strategic policy can not only prevent manipulation, but also incentivize agents to opt for improvement. Our findings shed light on the intertwined nature of microeconomic and ethical implications of firms' anticipation of strategic behavior when employing ML-driven decision systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。