Optimal Decision Making Under Strategic Behavior

Abstract

We are witnessing an increasing use of data-driven predictive models to inform decisions. As decisions have implications for individuals and society, there is increasing pressure on decision makers to be transparent about their decision policies. At the same time, individuals may use knowledge, gained by transparency, to invest effort strategically in order to maximize their chances of receiving a beneficial decision. Our goal is to find decision policies that are optimal in terms of utility in such a strategic setting. To this end, we first characterize how strategic investment of effort by individuals leads to a change in the feature distribution. Using this characterization, we first show that, in general, we cannot expect to find optimal decision policies in polynomial time and there are cases in which deterministic policies are suboptimal. Then, we demonstrate that, if the cost individuals pay to change their features satisfies a natural monotonicity assumption, we can narrow down the search for the optimal policy to a particular family of decision policies with a set of desirable properties, which allow for a highly effective polynomial time heuristic search algorithm using dynamic programming. Finally, under no assumptions on the cost individuals pay to change their features, we develop an iterative search algorithm that is guaranteed to find locally optimal decision policies also in polynomial time. Experiments on synthetic and real credit card data illustrate our theoretical findings and show that the decision policies found by our algorithms achieve higher utility than those that do not account for strategic behavior.

New method of estimating the outcome probabilities and setting the cost function values. New experiments on credit card data. Performance optimization in the presence of non-actionable features

References in corpus (9)

• Equality of Opportunity in Supervised Learning
• Actionable Recourse in Linear Classification
• The Disparate Effects of Strategic Manipulation
• Improving Information from Manipulable Data
• Deconvolving Feedback Loops in Recommender Systems
• Strategic Classification is Causal Modeling in Disguise
• Fair Decisions Despite Imperfect Predictions
• The Role of Randomness and Noise in Strategic Classification
• Consequential Ranking Algorithms and Long-term Welfare

Cited by in corpus (13)

• Causality for Machine Learning
• Strategic Classification is Causal Modeling in Disguise
• How Do Fair Decisions Fare in Long-term Qualification?
• Performative Prediction
• Decisions, Counterfactual Explanations and Strategic Behavior
• How to Learn when Data Reacts to Your Model: Performative Gradient Descent
• Causal Strategic Linear Regression
• From Predictions to Decisions: Using Lookahead Regularization
• Information Discrepancy in Strategic Learning
• Gaming Helps! Learning from Strategic Interactions in Natural Dynamics
• Counterfactual Explanations Can Be Manipulated
• Linear Classifiers that Encourage Constructive Adaptation
• Zeroth-Order Methods for Convex-Concave Minmax Problems: Applications to Decision-Dependent Risk Minimization