Gaming Helps! Learning from Strategic Interactions in Natural Dynamics

Yahav Bechavod, Katrina Ligett, Steven Wu, Juba Ziani
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:1234-1242, 2021.

Abstract

We consider an online regression setting in which individuals adapt to the regression model: arriving individuals may access the model throughout the process, and invest strategically in modifying their own features so as to improve their predicted score. Such feature manipulation, or “gaming”, has been observed in various scenarios—from credit assessment to school admissions, posing a challenge for the learner. Surprisingly, we find that such strategic manipulation may in fact help the learner recover the meaningful variables in settings where an agent can invest in improving meaningful features—that is, the features that, when changed, affect the true label, as opposed to non-meaningful features that have no effect. We show that even simple behavior on the learner’s part allows her to simultaneously i) accurately recover the meaningful features, and ii) incentivize agents to invest in these meaningful features, providing incentives for improvement.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-bechavod21a, title = { Gaming Helps! Learning from Strategic Interactions in Natural Dynamics }, author = {Bechavod, Yahav and Ligett, Katrina and Wu, Steven and Ziani, Juba}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {1234--1242}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/bechavod21a/bechavod21a.pdf}, url = {https://proceedings.mlr.press/v130/bechavod21a.html}, abstract = { We consider an online regression setting in which individuals adapt to the regression model: arriving individuals may access the model throughout the process, and invest strategically in modifying their own features so as to improve their predicted score. Such feature manipulation, or “gaming”, has been observed in various scenarios—from credit assessment to school admissions, posing a challenge for the learner. Surprisingly, we find that such strategic manipulation may in fact help the learner recover the meaningful variables in settings where an agent can invest in improving meaningful features—that is, the features that, when changed, affect the true label, as opposed to non-meaningful features that have no effect. We show that even simple behavior on the learner’s part allows her to simultaneously i) accurately recover the meaningful features, and ii) incentivize agents to invest in these meaningful features, providing incentives for improvement. } }
Endnote
%0 Conference Paper %T Gaming Helps! Learning from Strategic Interactions in Natural Dynamics %A Yahav Bechavod %A Katrina Ligett %A Steven Wu %A Juba Ziani %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-bechavod21a %I PMLR %P 1234--1242 %U https://proceedings.mlr.press/v130/bechavod21a.html %V 130 %X We consider an online regression setting in which individuals adapt to the regression model: arriving individuals may access the model throughout the process, and invest strategically in modifying their own features so as to improve their predicted score. Such feature manipulation, or “gaming”, has been observed in various scenarios—from credit assessment to school admissions, posing a challenge for the learner. Surprisingly, we find that such strategic manipulation may in fact help the learner recover the meaningful variables in settings where an agent can invest in improving meaningful features—that is, the features that, when changed, affect the true label, as opposed to non-meaningful features that have no effect. We show that even simple behavior on the learner’s part allows her to simultaneously i) accurately recover the meaningful features, and ii) incentivize agents to invest in these meaningful features, providing incentives for improvement.
APA
Bechavod, Y., Ligett, K., Wu, S. & Ziani, J.. (2021). Gaming Helps! Learning from Strategic Interactions in Natural Dynamics . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:1234-1242 Available from https://proceedings.mlr.press/v130/bechavod21a.html.

Related Material