Learning From Strategic Agents: Accuracy, Improvement, and Causality
Learning From Strategic Agents: Accuracy, Improvement, and Causality
复制标题
向战略代理学习：准确性、改进和因果关系
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Brian Axelrod
中科院分区：
文献类型：
--
作者：
Yonadav Shavit;Benjamin L. Edelman;Brian Axelrod
在许多预测性决策场景中，比如信用评分和学业测试，决策者必须构建一个模型（预测某些结果），该模型要考虑到行为主体为了获得更好决策而“操纵”自身特征的动机。然而，策略性分类文献通常假定行为主体的结果并非因果性地依赖于其特征（因此策略性行为是一种说谎形式），我们与同时期的研究一样，将行为主体的结果建模为其可变属性的函数。我们的公式首次纳入了一个关键现象：当行为主体采取行动改变可观测特征时，他们可能会作为一种副作用扰动隐藏特征，而这些隐藏特征会对其真实结果产生因果影响。
我们考虑决策者模型的三个不同的期望目标：准确预测行为主体操纵后的结果（准确性），激励行为主体改善这些结果（改进），以及在线性设定下，估计真实因果模型的可见系数（因果精度）。作为我们的主要贡献，我们提供了首批算法，用于直接从数据中学习准确性优化、改进优化和因果精度优化的线性回归模型，而无需事先了解行为主体可能采取的行动。这些算法通过允许决策者观察行为主体对一系列决策规则的反应，从而绕过了米勒等人（2019）的困难结果，实际上是诱导行为主体免费进行因果干预。
In many predictive decision-making scenarios, such as credit scoring and academic testing, a decision-maker must construct a model (predicting some outcome) that accounts for agents' incentives to "game" their features in order to receive better decisions. Whereas the strategic classification literature generally assumes that agents' outcomes are not causally dependent on their features (and thus strategic behavior is a form of lying), we join concurrent work in modeling agents' outcomes as a function of their changeable attributes. Our formulation is the first to incorporate a crucial phenomenon: when agents act to change observable features, they may as a side effect perturb hidden features that causally affect their true outcomes.
We consider three distinct desiderata for a decision-maker's model: accurately predicting agents' post-gaming outcomes (accuracy), incentivizing agents to improve these outcomes (improvement), and, in the linear setting, estimating the visible coefficients of the true causal model (causal precision). As our main contribution, we provide the first algorithms for learning accuracy-optimizing, improvement-optimizing, and causal-precision-optimizing linear regression models directly from data, without prior knowledge of agents' possible actions. These algorithms circumvent the hardness result of Miller et al. (2019) by allowing the decision maker to observe agents' responses to a sequence of decision rules, in effect inducing agents to perform causal interventions for free.
DOI：
10.1145/3351095.3372876
发表时间：
2020-01
期刊：
Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
影响因子：
--
作者：
S. Venkatasubramanian;M. Alfano
通讯作者：
S. Venkatasubramanian;M. Alfano