A Multi-Agent Prediction Market based on Partially Observable Stochastic Game

TL;DR

This paper introduces a game-theoretic model for multi-agent prediction markets using a partially observable stochastic game framework, providing a correlated equilibrium strategy that enhances price accuracy and agent utility.

Contribution

It develops a novel POSGI-based representation and a CE-based solution for multi-agent prediction markets, including extensions for risk-averse traders.

Findings

CE strategy outperforms five other strategies in simulations

Improves price prediction accuracy in prediction markets

Provides higher utilities for agents, including risk-averse ones

Abstract

We present a novel, game theoretic representation of a multi-agent prediction market using a partially observable stochastic game with information (POSGI). We then describe a correlated equilibrium (CE)-based solution strategy for this game which enables each agent to dynamically calculate the prices at which it should trade a security in the prediction market. We have extended our results to risk averse traders and shown that a Pareto optimal correlated equilibrium strategy can be used to incentively truthful revelations from risk averse agents. Simulation results comparing our CE strategy with five other strategies commonly used in similar markets, with both risk neutral and risk averse agents, show that the CE strategy improves price predictions and provides higher utilities to the agents as compared to other existing strategies.