An application of logistics regression model to determining the credit suitability and impacting factors in a special bank branch

Abstract

There are quite complicated rules and constraints that can be imposed by the
bank when the loan issued. Bank branches, which play a direct role in the credit,
must accurately determine the customer's credit request to eliminate these
difficulties and create an effective payment system according to the customer. In
the study, 100 random loan applications made in 2016 of a bank branch operating
in the Black Sea Region were examined. These customer demands are affecting
customer characteristics. The "Logistic Regression (LR) Model" was created to
predict creditworthiness according to the identified fugitives. In the model,
customer age, education, marital status, debt grade, credit card debt, other
debts, cross product are the variables. These are statistically significant in
terms of marital status, gender, cross product, or creditworthiness. However,
various variables such as debt income ratio, credit card debt, and other debts
are statistically significant and affect credibility to negatively. In addition,
occupational, income and educational constraints were found to be meaningless.
With this model, the factors affecting the credit were evaluated. As a result of
the study, the bank branch will benefit from the statistical model in which it is
created, to evaluate according to the customer characteristics in its portfolio,
and to give more credit to branch customers.

Keywords

• Bank,logistic regression (LR)

Kaynakça

1. [1] Atiya, Amir F. ”Bankruptcy prediction for credit risk using neural networks: A survey and new results.” IEEE Transactions on neural networks 12.4 (2001): 929-935.
2. [2] Maher, John J., and Tarun K. Sen. ”Predicting bond ratings using neural networks: a comparison with logistic regression.” Intelligent systems in accounting, finance and management 6.1 (1997): 59-72.
3. [3] Baesens, Bart, et al. ”Benchmarking state-of-the-art classification algorithms for credit scoring.” Journal of the operational research society 54.6 (2003): 627-635.
4. [4] Zekic-Susac,Marijana, Natasa Sarlija, andMirta Bensic. ”Small business credit scoring: a comparison of logistic regression, neural network, and decision tree models.” Information Technology Interfaces, 2004. 26th International Conference on. IEEE, 2004.
5. [5] Bensic, Mirta, Natasa Sarlija, and Marijana Zekic-Susac. ”Modelling small-business credit scoring by using logistic regression, neural networks and decision trees.” Intelligent Systems in Accounting, Finance and Management 13.3 (2005): 133-150.
6. [6] Su-juan, P. A. N. G. ”An application of logistic regression model in credit risk analysis.” Mathematics in Practice and Theory 9 (2006): 020.
7. [7] Lee, Tian-Shyug, et al. ”Mining the customer credit using classification and regression tree and multivariate adaptive regression splines.” Computational Statistics & Data Analysis50.4 (2006): 1113-1130.
8. [8] Ata, H. Ali. ”Banka Yabancilas¸masinin T¨urkiye’deki Yerli Ve Yabanci Bankalar Ac¸isindan Kars¸ilas¸tirilmasi.” Atat¨urk ¨Universitesi ˙Iktisadi ve ˙Idari Bilimler Dergisi 23.4 (2009).

9. [9] Dong, Gang, Kin Keung Lai, and Jerome Yen. ”Credit scorecard based on logistic regression with random coefficients.” Procedia Computer Science 1.1 (2010): 2463-2468.