Joint Scoring Rules: Zero-Sum Competition Avoids Performative Prediction

TL;DR

This paper shows that using zero-sum competition among multiple agents for joint scoring rules prevents manipulation and allows the principal to accurately identify and select their true preferred action.

Contribution

It introduces a zero-sum competition framework for joint scoring rules that overcomes the conflict of interest in predictive decision-making scenarios.

Findings

Zero-sum competition eliminates agent manipulation.

Training on zero-sum objectives improves predictive accuracy.

The approach is uniquely efficient and applicable under stochastic conditions.

Abstract

In a decision-making scenario, a principal could use conditional predictions from an expert agent to inform their choice. However, this approach would introduce a fundamental conflict of interest. An agent optimizing for predictive accuracy is incentivized to manipulate their principal towards more predictable actions, which prevents that principal from being able to deterministically select their true preference. We demonstrate that this impossibility result can be overcome through the joint evaluation of multiple agents. When agents are made to engage in zero-sum competition, their incentive to influence the action taken is eliminated, and the principal can identify and take the action they most prefer. We further prove that this zero-sum setup is unique, efficiently implementable, and applicable under stochastic choice. Experiments in a toy environment demonstrate that training on a zero-sum objective significantly enhances both predictive accuracy and principal utility, and can eliminate previously learned manipulative behavior.