Int. J. of Electronic Finance   »   2010 Vol.4, No.1

 

 

Title: Construction of classification models for credit policies in banks

 

Author: Kuang-Hsun Shih, Hsu-Feng Hung, Binshan Lin

 

Addresses:
Department of Banking and Finance, Chinese Culture University, 55, Hwa-Kang Road, Yang-Ming-Shan, Taipei 11114, Taiwan.
Department of Business Administration, National ChengChi University, 64, Sec. 2, ZhiNan Rd., Wenshan District, Taipei 11605, Taiwan.
College of Business Administration, Louisiana State University in Shreveport, One University Place, Shreveport, LA 71115, USA

 

Abstract: The execution and outcome of credit rating policies of banks are highly relevant to banks' decisions in investments, loans, and their measurement of default risks. They also have impacts on capital flows and utilisation of corporate borrowers. Therefore, it is essential to establish a scientific, objective, and accurate model of credit ratings for Customer Relationship Management (CRM) of the banking industry. The correct results of customers' ratings can serve as an important reference in the CRM of banks. This paper applies two classification methods, Multiple Discriminate Analysis (MDA) and Rough Set Theory (RST), to analyse and compare a total of 70 entries of corporate credit data. The result shows that the RST classification model boasts better classifying effects and is suitable for the analysis of credit ratings in the banking industry. This paper also suggests that a decision support system should be established with a scientific classification model in order to assist in the decisions and judgements of decision makers.

 

Keywords: credit policies; financial operation; classification models; decision support systems; DSS; bank credit ratings; multiple discriminate analysis; MDA; rough set theory; RST; customer relationship management; banking CRM.

 

DOI: 10.1504/IJEF.2010.030783

 

Int. J. of Electronic Finance, 2010 Vol.4, No.1, pp.1 - 18

 

Available online: 05 Jan 2010

 

 

Editors Full text accessAccess for SubscribersPurchase this articleComment on this article