Statistical risk assessment in bank lending to citizens
Abstract
In this article, construction of a logistic regression scoring model is presented as a statistical tool to determine the likelihood a borrower to fall into a state of failure. The study is done with Bulgarian real data. The main stages of modeling regression equation are described: sampling data modeling; statistical analysis of the data in terms of quality and completeness; selection of an appropriate logistic regression equation; analysis and evaluation of the performance of the selected regression model. The used data include information about citizens who are borrowers in the banking sector in Bulgaria. The data were processed by means of the statistical software IBM SPSS Statistics v19.
Keywords
JEL Classification
References
Draper, N. R. and H. Smith (1981). Applied Regression Analysis. 3rd ed. A Wiley-Interscience Publication: John Wiley & Sons Inc.
Feschijan, D. (2008). Analysis of the creditworthiness of bank loan applications. Fasta Universitats.
Finlay, S. (2010). Credit Scoring, Response Modelling and Insurance Rating - A practical guide to forecasting consumer behaviour. Palgrave Macmillan.
Gordon, L. (2013). Using classification and Regression Trees (CART) in SAS. University of Kentucky.
Gujarati, D. (2004). Basic Econometrics, Fourth Edition. The McGraw Hill Companies.
Hosmer, D. W. and S. Lemeshow (2000). Applied Logistic Regression, 2nd ed. New York: John Wiley & Sons Inc.
Lando, D. (2004). Credit Risk Modeling: Theory and Applications. Princeton: Princeton University Press.
Lund, B. and D. Brotherton (2013). Information Value Statistic. Detroit, MI, Paper AA-14-2013
Loh Wei-Yin (2011). Classification and regression trees. Department of Statistics, University of Wisconsin – Madison, USA: John Wiley & Sons Inc.
Madan, D. and H. Unal (1998). Pricing the risks of default. - Review of Derivatives Research, 2, р. 121-160.