Robust Strategic Classification under Decision-Dependent Cost Uncertainty
For researchers in algorithmic fairness and robust ML, this work extends strategic classification to realistic decision-dependent costs, though it is an incremental extension of existing robust optimization methods.
This paper addresses strategic classification where manipulation costs depend on past algorithmic decisions, proposing a two-stage robust optimization framework. The framework reduces uncertainty and curtails gaming compared to models with fixed costs.
Humans facing algorithmic decision systems have been found to ``game'' them by altering their input data (at a cost to them) in order to favorably change the algorithmic outcomes they receive (at a cost to the algorithm). The growing literature on strategic classification seeks to develop robust machine learning algorithms that account for, and reduce, unwanted strategic behavior. A limitation of these existing works is that they assume the cost of strategic behavior to be fixed and independent of the classifier's decision. In practice, however, manipulation costs evolve and depend on past algorithmic decisions: today's decisions influence tomorrow's costs. This paper proposes and analyzes a two-stage robust optimization framework with a decision-dependent uncertainty set to capture such dependencies. We highlight that awareness of policy-dependent costs not only reduces uncertainty, but also better curtails gaming of the algorithmic system over time.