Use of data mining algorithms to build scoring models

Rafał Bajek


Any decision to grant loan, it is fraught with risk. If the risk is higher, than the losses caused by an incorrect decision could be higher. Indeed, an important element is whether the person applying for a loan gives you the chance of its repayment. Consequently, collected some data which characterize the borrower and then the application is assessed by the scoring system and experts of the credit risk. To meet the scoring system due to its golas, can not be based on an accepted theory of rigid definition of "bad" clients. Using data mining methods we are looking for certain patterns in the data already collected under other loan applications.


data exploration; drilling data; credit scoring; data mining

Full Text:

PDF (Polski)


Matuszyk A.: Credit Scoring. CeDeWu, Warszawa 2008.

Janc A., Kraska M.: Credit-scoring, nowoczesna metoda oceny kredytowej. Biblioteka MenadGera, Warszawa 2001.

Hoffman F.: Comparing a genetic fuzzy and a neurofuzzy classifier for credit scoring, Computational Inteligent Systems do applied Researcg. Proceedings of the 5th International FLINS Conference, 2002, s. 355.

Stąpor K.: Automatyczna klasyfikacja obiektów, Exit, Warszawa 2005.

Krawiec K., Stefanowski J.: Uczenie maszynowe i sieci neuronowe. Wydawnictwo Politechniki Pozna1skiej, 2004.

Cichosz P.: Systemy uczące się. Wydawnictwo Naukowo-Techniczne, Warszawa 2000.

Anderson R.: The Credit Scoring Toolkit. Oxford University Press, New York 2007.

Thomas L. Edelman D., Crook J.: Credit Scoring and Its Applications. Society for Industrial and Applied Mathematics, Philadelphia 2002.

Written I., Frank E.: Data Mining: Practical Machine Learning Tools and Techniques. Second Edition, Elsevier, Francisco 2005.

Bradley A. P.: The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 1997.

Zuccaro C.: Classification and Prediction in Customer Scoring. Presentation at the Global Trends Conference, Academy of Business Administration, Cancum 2008.

Baesens B., Setiono R., Mues C., Vanthienen J.: Using Neural Network Rule Extraction and Decision Tables for Credit Risk Evaluation. Computer Journal of Management Science, vol. 49, no. 3, 2003, s. 312÷329.

Gestel T., Baesens B., Garcia J., Dijcke P.: A support Vector Machine Approach to Credit Scoring. Computer Journal of Bank en Financiewezen, vol. 2, no. 4, 2006, s. 73÷82.

Ming-Yi Sun, Szu-Fang Wang: Validation of Credit Rating Models - A Preliminary Look at Methodology and Literature Review. JCIC Risk Research Team Column, 2007.

Baesens B., Gestel T., Viane S., Stepanova M., Suykens J., Vanthienen J.: Benchmarking State of the Art Classification Algorithms for Credit Scoring. Computer Journal of the Operational Research Society, vol. 54, no. 3, 2003, s. 627÷635.