Strategic Classification is Causal Modeling in Disguise

John Miller, Smitha Milli, Moritz Hardt
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:6917-6926, 2020.

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. 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-miller20b, title = {Strategic Classification is Causal Modeling in Disguise}, author = {Miller, John and Milli, Smitha and Hardt, Moritz}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {6917--6926}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/miller20b/miller20b.pdf}, url = {https://proceedings.mlr.press/v119/miller20b.html}, 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. 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.} }
Endnote
%0 Conference Paper %T Strategic Classification is Causal Modeling in Disguise %A John Miller %A Smitha Milli %A Moritz Hardt %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-miller20b %I PMLR %P 6917--6926 %U https://proceedings.mlr.press/v119/miller20b.html %V 119 %X 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. 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.
APA
Miller, J., Milli, S. & Hardt, M.. (2020). Strategic Classification is Causal Modeling in Disguise. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:6917-6926 Available from https://proceedings.mlr.press/v119/miller20b.html.

Related Material