Anticipating Gaming to Incentivize Improvement: Guiding Agents in (Fair) Strategic Classification
This addresses fairness and strategic behavior in machine learning for critical decision-making applications, representing an incremental advance in strategic classification.
The paper tackles the problem of individuals choosing between genuine improvement and deceptive manipulation in response to algorithmic decision systems, and finds that a firm's anticipation of strategic behavior can lead to fair classifiers that incentivize improvement over manipulation.
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 highlight the impact of the firm's anticipation of strategic behavior, identifying when and why a (fair) strategic policy can not only prevent manipulation, but also incentivize agents to opt for improvement.