English

Strategic Classification is Causal Modeling in Disguise

Machine Learning 2020-02-19 v3 Machine Learning

Abstract

Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic adaptation as gaming and attempted to mitigate its effects, recent work has instead sought to design classifiers that incentivize individuals to improve a desired quality. Key to both accounts is a cost function that dictates which adaptations are rational to undertake. In this work, we develop a causal framework for strategic adaptation. Our causal perspective clearly distinguishes between gaming and improvement and reveals an important obstacle to incentive design. We prove any procedure for designing classifiers that incentivize improvement must inevitably solve a non-trivial causal inference problem. Moreover, we show a similar result holds for designing cost functions that satisfy the requirements of previous work. With the benefit of hindsight, our results show much of the prior work on strategic classification is causal modeling in disguise.

Keywords

Cite

@article{arxiv.1910.10362,
  title  = {Strategic Classification is Causal Modeling in Disguise},
  author = {John Miller and Smitha Milli and Moritz Hardt},
  journal= {arXiv preprint arXiv:1910.10362},
  year   = {2020}
}

Comments

This paper was previously titled "Strategic Adaptation to Classifiers: A Causal Perspective." The current version subsumes all previous versions

R2 v1 2026-06-23T11:52:10.357Z