General Bayesian Predictive Synthesis

TL;DR

This paper introduces General Bayesian Predictive Synthesis (GBPS), a novel Bayesian ensemble method that integrates expert predictive distributions without parameter estimation, aiming to enhance decision-making quality.

Contribution

The paper proposes GBPS, a new Bayesian ensemble approach based on loss minimization, differing from existing methods that rely on parameter estimation.

Findings

GBPS effectively combines expert predictions in simulations.

GBPS improves decision accuracy over traditional ensemble methods.

The method is flexible and does not require parameter estimation.

Abstract

This study investigates Bayesian ensemble learning for improving the quality of decision-making. We consider a decision-maker who selects an action from a set of candidates based on a policy trained using observations. In our setting, we assume the existence of experts who provide predictive distributions based on their own policies. Our goal is to integrate these predictive distributions within the Bayesian framework. Our proposed method, which we refer to as General Bayesian Predictive Synthesis (GBPS), is characterized by a loss minimization framework and does not rely on parameter estimation, unlike existing studies. Inspired by Bayesian predictive synthesis and general Bayes frameworks, we evaluate the performance of our proposed method through simulation studies.