Performative Prediction on Games and Mechanism Design

TL;DR

This paper investigates how predictions influence collective actions in strategic settings, revealing that stable accurate forecasts can harm social welfare, and proposes mechanisms to improve outcomes considering agent behavior.

Contribution

It introduces a model of performative prediction in strategic environments, analyzing the impact on social welfare and proposing mechanisms to optimize trade-offs.

Findings

Stable accurate predictions can reduce social welfare.

Knowledge of agent behavior enables better prediction mechanisms.

Mechanism design can improve collective outcomes.

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.