Causal Strategic Classification: A Tale of Two Shifts

Guy Horowitz, Nir Rosenfeld
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:13233-13253, 2023.

Abstract

When users can benefit from certain predictive outcomes, they may be prone to act to achieve those outcome, e.g., by strategically modifying their features. The goal in strategic classification is therefore to train predictive models that are robust to such behavior. However, the conventional framework assumes that changing features does not change actual outcomes, which depicts users as "gaming" the system. Here we remove this assumption, and study learning in a causal strategic setting where true outcomes do change. Focusing on accuracy as our primary objective, we show how strategic behavior and causal effects underlie two complementing forms of distribution shift. We characterize these shifts, and propose a learning algorithm that balances between these two forces and over time, and permits end-to-end training. Experiments on synthetic and semi-synthetic data demonstrate the utility of our approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-horowitz23a, title = {Causal Strategic Classification: A Tale of Two Shifts}, author = {Horowitz, Guy and Rosenfeld, Nir}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {13233--13253}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/horowitz23a/horowitz23a.pdf}, url = {https://proceedings.mlr.press/v202/horowitz23a.html}, abstract = {When users can benefit from certain predictive outcomes, they may be prone to act to achieve those outcome, e.g., by strategically modifying their features. The goal in strategic classification is therefore to train predictive models that are robust to such behavior. However, the conventional framework assumes that changing features does not change actual outcomes, which depicts users as "gaming" the system. Here we remove this assumption, and study learning in a causal strategic setting where true outcomes do change. Focusing on accuracy as our primary objective, we show how strategic behavior and causal effects underlie two complementing forms of distribution shift. We characterize these shifts, and propose a learning algorithm that balances between these two forces and over time, and permits end-to-end training. Experiments on synthetic and semi-synthetic data demonstrate the utility of our approach.} }
Endnote
%0 Conference Paper %T Causal Strategic Classification: A Tale of Two Shifts %A Guy Horowitz %A Nir Rosenfeld %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-horowitz23a %I PMLR %P 13233--13253 %U https://proceedings.mlr.press/v202/horowitz23a.html %V 202 %X When users can benefit from certain predictive outcomes, they may be prone to act to achieve those outcome, e.g., by strategically modifying their features. The goal in strategic classification is therefore to train predictive models that are robust to such behavior. However, the conventional framework assumes that changing features does not change actual outcomes, which depicts users as "gaming" the system. Here we remove this assumption, and study learning in a causal strategic setting where true outcomes do change. Focusing on accuracy as our primary objective, we show how strategic behavior and causal effects underlie two complementing forms of distribution shift. We characterize these shifts, and propose a learning algorithm that balances between these two forces and over time, and permits end-to-end training. Experiments on synthetic and semi-synthetic data demonstrate the utility of our approach.
APA
Horowitz, G. & Rosenfeld, N.. (2023). Causal Strategic Classification: A Tale of Two Shifts. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:13233-13253 Available from https://proceedings.mlr.press/v202/horowitz23a.html.

Related Material