Performative Prediction on Games and Mechanism Design
This work addresses the impact of performative prediction on social welfare in scenarios like pandemic predictions and election polls, offering a novel approach for mechanism design, though it is incremental as a first step in considering interdependencies.
The paper tackles the problem of performative prediction in interdependent agent settings, such as collective risk dilemmas, where predictions influence outcomes and social welfare. It demonstrates that stable accurate predictions can minimize social welfare with high probability and proposes a Bayesian agent model to achieve better trade-offs for mechanism design.
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.