Performative Prediction on Games and Mechanism Design

António Góis, Mehrnaz Mofakhami, Fernando P. Santos, Gauthier Gidel, Simon Lacoste-Julien
Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258:1855-1863, 2025.

Abstract

Agents often have individual goals which depend on a group’s actions. If agents trust a forecast of collective action and adapt strategically, such prediction can influence outcomes non-trivially, resulting in a form of performative prediction. This effect is ubiquitous in scenarios ranging from pandemic predictions to election polls, but existing work has ignored interdependencies among predicted agents. As a first step in this direction, we study a collective risk dilemma where agents dynamically decide whether to trust predictions based on past accuracy. As predictions shape collective outcomes, social welfare arises naturally as a metric of concern. We explore the resulting interplay between accuracy and welfare, and demonstrate that searching for stable accurate predictions can minimize social welfare with high probability in our setting. By assuming knowledge of a Bayesian agent behavior model, we then show how to achieve better trade-offs and use them for mechanism design.

Cite this Paper

BibTeX
@InProceedings{pmlr-v258-gois25a, title = {Performative Prediction on Games and Mechanism Design}, author = {G{\'o}is, Ant{\'o}nio and Mofakhami, Mehrnaz and Santos, Fernando P. and Gidel, Gauthier and Lacoste-Julien, Simon}, booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics}, pages = {1855--1863}, year = {2025}, editor = {Li, Yingzhen and Mandt, Stephan and Agrawal, Shipra and Khan, Emtiyaz}, volume = {258}, series = {Proceedings of Machine Learning Research}, month = {03--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v258/main/assets/gois25a/gois25a.pdf}, url = {https://proceedings.mlr.press/v258/gois25a.html}, abstract = {Agents often have individual goals which depend on a group’s actions. If agents trust a forecast of collective action and adapt strategically, such prediction can influence outcomes non-trivially, resulting in a form of performative prediction. This effect is ubiquitous in scenarios ranging from pandemic predictions to election polls, but existing work has ignored interdependencies among predicted agents. As a first step in this direction, we study a collective risk dilemma where agents dynamically decide whether to trust predictions based on past accuracy. As predictions shape collective outcomes, social welfare arises naturally as a metric of concern. We explore the resulting interplay between accuracy and welfare, and demonstrate that searching for stable accurate predictions can minimize social welfare with high probability in our setting. By assuming knowledge of a Bayesian agent behavior model, we then show how to achieve better trade-offs and use them for mechanism design.} }
Endnote
%0 Conference Paper %T Performative Prediction on Games and Mechanism Design %A António Góis %A Mehrnaz Mofakhami %A Fernando P. Santos %A Gauthier Gidel %A Simon Lacoste-Julien %B Proceedings of The 28th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2025 %E Yingzhen Li %E Stephan Mandt %E Shipra Agrawal %E Emtiyaz Khan %F pmlr-v258-gois25a %I PMLR %P 1855--1863 %U https://proceedings.mlr.press/v258/gois25a.html %V 258 %X Agents often have individual goals which depend on a group’s actions. If agents trust a forecast of collective action and adapt strategically, such prediction can influence outcomes non-trivially, resulting in a form of performative prediction. This effect is ubiquitous in scenarios ranging from pandemic predictions to election polls, but existing work has ignored interdependencies among predicted agents. As a first step in this direction, we study a collective risk dilemma where agents dynamically decide whether to trust predictions based on past accuracy. As predictions shape collective outcomes, social welfare arises naturally as a metric of concern. We explore the resulting interplay between accuracy and welfare, and demonstrate that searching for stable accurate predictions can minimize social welfare with high probability in our setting. By assuming knowledge of a Bayesian agent behavior model, we then show how to achieve better trade-offs and use them for mechanism design.
APA
Góis, A., Mofakhami, M., Santos, F.P., Gidel, G. & Lacoste-Julien, S.. (2025). Performative Prediction on Games and Mechanism Design. Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 258:1855-1863 Available from https://proceedings.mlr.press/v258/gois25a.html.

Related Material