Performative Prediction on Games and Mechanism Design

António Góis, Mehrnaz Mofakhami, Fernando P. Santos, Simon Lacoste-Julien, Gauthier Gidel

TL;DR: Study of a new game-theoretic performative prediction setting with a) interdependence among predicted agents, b) dynamic trust in predictions and c) interactions between accuracy and agents' goals.

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.

Submission Number: 623