A MULTIPLE INTELLIGENT AGENT SYSTEM FOR CREDIT RISK PREDICTION VIA AN OPTIMIZATION OF LOCALIZED GENERALIZATION ERROR WIT

Company bankruptcies cost billions of dollars in losses to banks each year. Thus credit risk prediction is a critical part of a bank's loan approval decision process. Traditional financial models for credit risk 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 credit risk based on only partial information of the company. Each of the agents is an expert, but has limited knowledge (represented by features) about the company. The decisions of all agents are combined together to form a final credit risk prediction. Experiments show that our model out-performs other existing methods using the benchmarking Compustat American Corporations dataset.

作 者： Daniel S. YEUNG Wing W. Y. NG Aki P. F. CHAN Patrick P. K. CHAN Michael FIRTH Eric C. C. TSANG   作者單位： Daniel S. YEUNG(Media and Life Science Computing Laboratory, Shenzhen Graduate School,Harbin Institute of Technology, Shenzhen, 518055, China)

Wing W. Y. NG(Media and Life Science Computing Laboratory, Shenzhen Graduate School,Harbin Institute of Technology, Shenzhen, 518055, China;Department of Computing, Hong Kong Polytechnic University, Hong Kong, China)

Aki P. F. CHAN,Patrick P. K. CHAN,Eric C. C. TSANG(Department of Computing, Hong Kong Polytechnic University, Hong Kong, China)

Michael FIRTH(Department of Finance and Insurance, Lingnan University, Hong Kong) 

刊 名： 系統科學與系統工程學報（英文版）  英文刊名： JOURNAL OF SYSTEMS SCIENCE AND SYSTEMS ENGINEERING  年，卷(期)： 2007 16(2)  分類號： N94  關鍵詞： Credit rating   business intelligence   localized generalization error   multiple classifier system   feature grouping  

【A MULTIPLE INTELLIGENT AGENT SYSTEM 】相關文章：

A General Method for QTL Mapping in Multiple Related Populations Derived from Multiple Parents04-26

Selling Agent 銷售代理05-04

Chinas Meteorological Satellite Application System04-26

基于Agent方法體系的ODSS研究04-27

CASC To Build A New Aerospace Industrial System By 201504-26

Decomposition characteristics of toluene by a corona radical shower system04-26

Degradation of 4-CP in an internal electrolysis system04-26

Degradation of 4-CP in an internal electrolysis system04-26

Fuzzy Multiple Attribute Decision Making for Evaluating Aggregate Risk in Green Manufacturing04-26

基于多 Agent 協商機制的沖突解脫方法04-27