Using support vector machine in credit scorecard development
Keywords:
datamining, support vector machine, Basel IIAbstract
Support vector machines, came into alive from statistical learning theory, means a new stage in the evoution of datamining algorithms. The method handle the problem of classification in a very natural way, and promise growth is the efficiency of learning statistical patterns. However in Basel II required parameter estimation and in credit scorecard development support vector machines are not wide range used. In this paper it will be shown how to use SVMs for calculating probability of default, placing emphasis on business understanding and impact on expected loss calculation.
References
Basel Comittee on Banking Supervision (2004). Basel II: International Convergence of Capital Measurement and Capital Standards: a Revised Framework
Basel Comittee on Banking Supervision (2005). Studies on Validation of Internal Rating Systems
Hsu, C. W., Chang, C. C., Lin, C. J. (2008): A Practical Guide to Support Vector Classification, Department of Computer Science, National Taiwan University, Taipei 106, Taiwan.
Engelmann, B., Hayden, E., Tasche, D. (2003). Testing rating accuracy.
Quinlan, S. (1987): Simplifying decision trees, Int J Man-Machine Studies, 27. 3. 221–234. https://doi.org/10.1016/S0020-7373(87)80053-6
Quinlan, S. (1992): C4.5: Programs for Machine Learning, Morgan Kaufmann R-Project: http://www.r-project.org
Sobehart, J., Keenan, S., Stein, R. (2000). Validation methodologies for default risk models. Credit, 51–56.
Sobehart, J., Keenan, S. (2001). Measuring default accurately, Risk, S31–S33, 2001. March
Szücs I. (2007). Unstable regions in the scorecards’ input space, Business Sciences – Symposium for Young
Szücs I., Pitlik L. (2007). Lakossági termékvásárlási modellek és viselkedési hitelpontozó kártyák fejlesztése makrogazdasági peremfeltételekkel, Acta Agraria Kaposváriensis, 11. 2. 153–163.
Researchers, Budapest Tech of Hungary, 181–186 pp.
Vapnik V. (1998): Statistical learning theory, John Wiley & Sons, Inc., USA
Downloads
Published
Issue
Section
License
Copyright (c) 2010 Szücs Imre
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
