Multi-agent hybrid mechanism for financial risk management

Abstract

Purpose: The goal of this study was to propose the multi-agent mechanism to forecast the corporate financial distress. Design/methodology/approach: This study utilized numerous methods, namely random subspace method, discriminant analysis and decision tree to construct the multi-agent forecasting model. Findings: The study shows a superior forecasting performance. Originality/value: The use of multi-agent model to predict the corporate financial distress.