Credit Card Risk Assessment Using Artificial Neural Networks
In recent years, the supply and demand of the plastic currency market has been rapidly increasing, especially, for the growth rate in the credit card market. It has increased about 16 times in the last 10 years. Many banks devoted to make a large investment in credit card marketing for the sake of getting the maximum profits in the worldwide market. However, most banks are trying to reduce the requirements for credit card application in order to increase the motivation of the customers for applying their credit cards. As a result, many banks somehow ignore the risk management of credit card approval which leads to the increases of bad debt in the credit card market. When this scenario happens year by year, those banks will not get profits from the credit card market but a great loss.
In this study, a total of 113,048 entries were used which included fundamental customer data, credit card data, and customer history data from Joint Credit Information Center (JCIC) of Taiwan. We used the characteristics of artificial neural networks and grey theory to find out the potential factors of the bad credit and finally used the correlation method to find out the higher (important) relative variables (parameters) of bad credit. 80,000 entries were randomly selected as training data and the remaining 33,084 entries were used as testing data.
The experimental results shown that the accuracy of forecasting rate for the proposed early warning system was an overall of 92.7%. These results suggested that the once the collections of the new customer data were available, the proposed approach could be used as an early warning system which can be used to decrease the risk of credit card approval.
Joint credit information center, Taiwan, http://www.jcic.org.tw/index.htm
J. S. Rosenbloom, “A case study in T. Khabaza and C. Shearer (1995), Data mining with clementine,” integral Solutions Limited, 1972.
C. A. Williams and R. M. Henis, Risk man-agement and insurance, 4th ed., New York: McGraw-Hill, 1981.
C. R. Lin, Finance innovation and risk man-agement, 1st ed., 1997.
R. A. Neibet, “How to choose a data mining suite,”http://www.dmreview.com/article_sub.cfm?articleID=1000465, 2004.
T. Kohonen, Self-organizing maps, 3rd ed. Springer, Berlin, Heidelberg, 2001.
C. L. Teng, H. Kuo, Grey theory and its appli-cation, 1996.
J. N. Crook, D. B. Edelman, L. C. Thomas, “Recent developments in consumer credit risk assessment,” European Journal of Operational Research, vol. 183, no. 3, 16, pp. 1447-1465, December 2007
L. Yu, S. Wang, K. K. Lai,“2007 Credit risk assessment with a multistage neural network ensemble learning approach,” Expert Systems with Applications, vol. 34, no. 2, pp. 1434-1444, February 2008
B. Twala, “Multiple classifier application to credit card risk assessment,” Expert Systems with Applications, vol. 37, no. 4, pp. 3326-3336, April 2010.
Submission of a manuscript implies: that the work described has not been published before that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication. Authors can retain copyright of their article with no restrictions. Also, author can post the final, peer-reviewed manuscript version (postprint) to any repository or website.
Since Oct. 01, 2015, PETI will publish new articles with Creative Commons Attribution Non-Commercial License, under The Creative Commons Attribution Non-Commercial 4.0 International (CC BY-NC 4.0) License.
The Creative Commons Attribution Non-Commercial (CC-BY-NC) License permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes