Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach

Company Bankruptcy costs a loss of billions of dollars to banks each year. Thus bankruptcy prediction is a critical part of a bank's loan approval decision process. Traditional financial models for bankruptcy prediction are no longer adequate for describing today's complex relationship between the financial health and potential bankruptcy of a company. In this work, a multiple classifier system (embedded in a multiple intelligent agent system) is proposed to predict the financial health of a company. In our model, each individual agent (classifier) makes a prediction on the likelihood of bankruptcy based on only partial information of the company. Each of the agents is an expert, having certain part of the knowledge (represented by features) of the company. The decisions of all agents are combined together to form a final bankruptcy prediction. Preliminary experiments show that our model out-performs other existing methods using the benchmarking Compustat American Corporations dataset.