Strategic Classification is Causal Modeling in Disguise

TL;DR

This paper introduces a causal framework for strategic classification, revealing that designing classifiers to incentivize improvement inherently involves solving complex causal inference problems, thus reinterpreting prior work as causal modeling.

Contribution

It develops a causal perspective on strategic adaptation, demonstrating the intrinsic link between incentive design and causal inference in classification tasks.

Findings

Designing incentive-compatible classifiers requires solving causal inference problems.

Prior approaches to strategic classification are essentially causal modeling.

There is an inherent obstacle in designing cost functions that promote improvement.

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.