Title: A comparison of traditional and Simple Artificial Immune System (SAIS) techniques in consumer credit scoring

Authors: Kevin Leung, France Cheong, Christopher Cheong

Addresses: Faculty of Business, School of Business Information Technology, RMIT University, Level 17, 239-251 Bourke Street, Melbourne, Victoria 3000, Australia. ' Faculty of Business, School of Business Information Technology, RMIT University, Level 17, 239-251 Bourke Street, Melbourne, Victoria 3000, Australia. ' Faculty of Business, School of Business Information Technology, RMIT University, Level 17, 239-251 Bourke Street, Melbourne, Victoria 3000, Australia

Abstract: Credit scoring has become a very important task in the credit industry and its use has increased at a phenomenal speed through the mass issue of credit cards since the 1960s. This paper compares the classification performance of the most commonly used traditional statistical as well as intelligent systems techniques against a new artificial intelligence method based on the natural immune system principles, named Simple Artificial Immune System (SAIS). Experiments are performed on three benchmark credit datasets and SAIS was found to be a very competitive technique for developing scorecards.

Keywords: consumer credit scoring; intelligent systems; traditional statistical techniques; artificial immune systems; classification performance; artificial intelligence; scorecards.

DOI: 10.1504/IJAISC.2010.032510

International Journal of Artificial Intelligence and Soft Computing, 2010 Vol.2 No.1/2, pp.1 - 25

Published online: 04 Apr 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article