A New Method for Clustering in Credit Scoring Problems


Authors

Mohammad Reza Gholamian - School of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran. Saber Jahanpour - Department of financial management, Shahid Beheshti University, Tehran, Iran. Seyed Mahdi Sadatrasoul - School of Industrial Engineering, Iran University of Science and Technology, Tehran, Iran.


Abstract

Due to the recent financial crisis and regulatory concerns of Basel II, credit risk assessment has become one of the most important topics in the financial risk management. Quantitative credit scoring models are widely used to assess credit risk in financial institutions. In this paper we introduce Time Adaptive self organizing Map Neural Network to cluster creditworthy customers against non credit worthy ones. We test this Neural Network on Australian credit data set and compare the results with other clustering Algorithm’s include K-means, PAM, SOM against different internal and external measures. TASOM has the best performance in clusters customers.


Share and Cite

  • Share on Facebook
  • Share on Twitter
  • Share on LinkedIn
ISRP Style

Mohammad Reza Gholamian, Saber Jahanpour, Seyed Mahdi Sadatrasoul, A New Method for Clustering in Credit Scoring Problems, Journal of Mathematics and Computer Science, 6 (2013), no. 2, 97-106

AMA Style

Gholamian Mohammad Reza, Jahanpour Saber, Sadatrasoul Seyed Mahdi, A New Method for Clustering in Credit Scoring Problems. J Math Comput SCI-JM. (2013); 6(2):97-106

Chicago/Turabian Style

Gholamian, Mohammad Reza, Jahanpour, Saber, Sadatrasoul, Seyed Mahdi. "A New Method for Clustering in Credit Scoring Problems." Journal of Mathematics and Computer Science, 6, no. 2 (2013): 97-106


Keywords


MSC


References