Presenting the smart pattern of credit risk of the real banks’ customers using machine learning algorithm.

الموضوعات :

Hojjat Tajik ¹ (Department of Accounting. Qeshm branch, Islamic Azad University. Qeshm, Iran.)
Ghodratollah Talebnia ² (Department of Accounting. Science and research branch, Islamic Azad University. Tehran, Iran.)
Hamid Reza Vakili Fard ³ (Department of Accounting. Science and research branch, Islamic Azad University. Tehran, Iran.)
Faegh Ahmadi ⁴ (Department of Accounting. Science and research branch, Islamic Azad University. Tehran, Iran.)

تاريخ الإرسال : 24 الخميس , جمادى الثانية, 1443 تاريخ التأكيد : 09 الأحد , رمضان, 1443 تاريخ الإصدار : 16 الجمعة , صفر, 1445

الکلمات المفتاحية: bank customers’ risk, Smart pattern, Credit Risk, Random forest algorithm, Machine Learning,

ملخص المقالة :

In the past, deciding over granting loans to bank customers in Iran would be made traditionally and based on personal judgments over the risk of repayment. However, increase in demands on banking facilities by economic enterprises and families on the one side, and increased as well as extended commercial competitions among banks and financial and credit institutions in the country for reduction of facility repayment risk on the other side, have caused application of novel methods such as some statistical ones in this context. Now to predict the risk of negligence in banking facility repayment and classification of the candidates, bankers use their customers’ credit ranking. Time efficiency, cost effectiveness, avoidance from personal judgments, and further accuracy in examining the candidates who apply for various funds are of its salient merits of this new combined method. Various statistical methods including biased analysis, logistic regression, non-parametric parallelism, and also some others such as neural networks have been employed for credit ranking. In this research, given the random forest metaheuristic algorithm-based smart pattern of real bank customers’ credit risk (case study: Bank Tejarat) was presented. According to the value of skewness, the data could be stated to have a normal distribution. Based on the observed results, the lowest mean was related to the variable of type of facility and its maximum value, to the amount of facility.

المصادر:

• Rajabzadeh Moghani, N., Lotfalipour, M., Seifi, A., Razmkhah, M., The Study of Factors Affecting on Credit Risk of Bank Customers Using Non-Parametric and Semi-Parametric Survival Analysis Models, Monetary and Financial Economics, 2017, 24(14), P.88-123. Doi: 10.22067/pm. v24i13.52294.

 

• Shirin Bakhsh Masooleh, Sh., Yousefi, N., Ghornan Zadeh, J., Investigating the factors affecting the probability of non-repayment of credit facilities (case study of legal customers in Iran Export Development Bank), Quarterly Journal of Securities Analysis, 2011, 4(12), P. 111-137.

 

• Chen, W., Xiang, G., Liu, Y., Wang, K., Credit risk Evaluation by hybrid data mining technique, Systems Engineering Procedia, 2012, 3, P. 194-200. Doi: 10.1016/j.sepro.2011.10.029.

 

• Wang, Y., Zhang, Y., Lu, Y., Yu, X., A Comparative Assessment of Credit Risk Model Based on Machine Learning-a case study of bank loan data, Procedia Computer Science, 2020, 174, P. 141-9.

      Doi: 10.1016/j.procs.2020.06.069.

 

• Tsai, C.F., Wu, J.W., Using neural network ensembles for bankruptcy prediction and credit scoring, Expert systems with applications, 2008, 34(4), P.2639-49. Doi: 10.1016/j.eswa.2007.05.019.

 

• Mhlanga, D., Financial inclusion in emerging economies: The application of machine learning and artificial intelligence in credit risk assessment, International Journal of Financial Studies, 2021, 9(3), P. 39.

        Doi: 10.3390/ijfs9030039.

 

• Shahari, F., Zakaria, R.H., Rahman, M.S., Investigation of the expected loss of sharia credit instruments in global Islamic banks, International journal of managerial finance, 2015. Doi: 10.1108/IJMF-12-2014-0196.

 

• Louzada F, Ferreira-Silva PH, Diniz CA. On the impact of disproportional samples in credit scoring models: An application to a Brazilian bank data. Expert Systems with Applications. 2012, 39(9), P. 8071-8.

        Doi: 10.1016/j.eswa.2012.01.134.

• Singh, S., Murthi, B. P. S., Steffes, E., Developing a measure of risk adjusted revenue (RAR) in credit cards market: Implications for customer relationship management, European Journal of Operational Research, 2013, 224(2), P. 425-434. Doi: 10.1016/j.ejor.2012.08.007.

 

• Pandey, MK., Mittal, M., Subbiah, K., Optimal balancing and efficient feature ranking approach to minimize credit risk, International Journal of Information Management Data Insights, 2021, 1(2), P: 100037.

       Doi: 10.1016/j.jjimei.2021.100037.

 

• Doko, F., Kalajdziski, S., Mishkovski, I., Credit risk model based on central bank credit registry data, Journal of Risk and Financial Management, 2021, 14(3), P.138. Doi: 10.3390/jrfm14030138.

 

• Smith, P.F., Ganesh, S., Liu, P., A comparison of random forest regression and multiple linear regression for prediction in neuroscience, Journal of neuroscience methods, 2013, 220(1), P. 85-91.

        Doi: 10.1016/j.jneumeth.2013.08.024.

 

• Polamuri, S., How the random forest algorithm works in machine learning? Retrieved December, 2017, P. 21.

 

• Dong, G, Lai, KK., Yen, J., Credit scorecard based on logistic regression with random coefficients, Procedia Computer Science, 2010, 1(1), P.2463-8. Doi: 10.1016/j.procs.2010.04.278.

 

• Witzany, JM., Rychnovský, M., Charamza, P., Survival Analysis in LGD Modeling, European Financial and Accounting Journal, 2012, 7(1), P. 6-27, Doi: 10.18267/j.efaj.12.

 

• Addo, P.M., Guegan, D., Hassani, B., Credit risk analysis using machine and deep learning models Risks, 2018, 6(2), P. 38. Doi: 10.3390/risks6020038.

 

• Witkowska, D., Discrete choice model application to the credit risk evaluation, International Advances in Economic Research, 2006, 12(1), P.33-42. Doi: 10.1007/s11294-006-6124-0.

 

• Grace, AM., Williams, SO., Comparative analysis of neural network and fuzzy logic techniques in credit risk evaluation, International Journal of Intelligent Information Technologies (IJIIT), 2016, 12(1), P.47-62.

        Doi: 10.4018/IJIIT.2016010103.

 

• Huang, C.L., Chen, M.C., Wang, C.J., Credit scoring with a data mining approach based on support vector machines, Expert Syst, Appl, 2010, 33(4), P.847–856. Doi: 10.1016/j.eswa.2006.07.007.

 

• Yurdakul, F., Macroeconomic modelling of credit risk for banks, Procedia-Social and behavioral sciences, 2014, 109, P. 784-93.

 

• Shen, F., Ma, X., Li, Z., Xu, Z., Cai, D., An extended intuitionistic fuzzy TOPSIS method based on a new distance measure with an application to credit risk evaluation, Information Sciences, 2018, 428, P. 105-19.

       Doi: 10.1016/j.ins.2017.10.045.

 

• Lappas, P.Z., Yannacopoulos, A.N., A machine learning approach combining expert knowledge with genetic algorithms in feature selection for credit risk assessment, Applied Soft Computing, 2021, 107, P.107391. Doi: 10.1016/j.asoc.2021.107391.

 

• Pandimurugan, V., Usha, D., Guptha, MN., Hema, MS., Random forest tree classification algorithm for predicating loan, Materials Today: Proceedings, 2021, Doi: 10.1016/j.matpr.2021.12.322.

 

• Machado, M.R, Karray, S., Assessing credit risk of commercial customers using hybrid machine learning algorithms, Expert Systems with Applications, 2022, P. 116889. Doi: 10.1016/j.eswa.2022.116889.

 

• García-Céspedes, R., Moreno, M., The generalized Vasicek credit risk model: A Machine Learning approach. Finance Research Letters, 2022, P. 102669. Doi: 10.1016/j.frl.2021.102669.

 

• Nazar Aghaei, M., Ghiasi, H., Asgharkhah, M., Credit risk categories of real customers using collective learning (Case study of Sepah Bank), Money-Banking Journal, 2019, 12(39), P. 129-166.

 

• Del Afrooz, N., Homayoon Far, M., Taghi Poor Tamijani, M., Credit Risk Management in Banks Using Combined Approach, Quarterly Journal of Financial Engineering and Securities Management, 2019, 10(38), P. 94-116. Doi:  20.1001.1.22519165.1398.10.38.5.1.

 

• Khojasteh, G., Daee Karimzade, S., Sharifi Ranani, H., Credit Rating of Real Customers of the Bank with a Combined Approach of Logistic-Symbolic Regression (Case Study: Ghavamin Bank of Shiraz), Resource Management in Police Journal of the Management Dept, 2019, (3), P. 117-48.

 

• Mohaghegh Nia, M., J., Dehghan Dehnavi, M., A., Bayi, M., The effect of internal and external factors of banking industry on bank credit risk in Iran, Journal of Financial Economics, 2019, 13(46), P. 127-144.

 

• Heidari, M., S., Ebrahimi, B., Mohebi, N., Credit Risk Modeling of Basket Bank Credit Facility Basket using Actuary Modeling, Journal of Financial science of securities analysis, 2017, 10(34), P. 55-71.

 

• Salehi, M., Kurd Kanouli, A., Choosing optimal features to determine the credit risk of bank customers, Quarterly Journal of Smart Business Management, 2017, 6(22), P. 129-154.

 

• Gholi Poor, S., Amoozadeh Khalili, H., Haji Aghaei, M., Credit risk assessment of the real customers
  of the bank using logistic regression and neural network (case study of Tourism Bank Branch),
  The third World Conference on Management, Economics of Accounting and Humanities at the beginning of the third millennium, Shiraz, in cooperation with the Institute of Higher Education Institute of Allameh Khoyi University, Zarghan University of Research in the Conference, 2016.

 

• Mir Ghafoori, H., Ashoori, Z., Credit risk assessment of bank customers. Business Management Explorations, 2015, 7(13), P. 147-166.

 

• Hoseini, A., Zibaei, M., Credit Risk Management at the Mamasani Agricultural Bank using the
  Neural Network Model, Journal of Agricultural Economics, 2015, 9(2), P. 103-119.

 

• Ghodsi Poor, H., Salari, M., Delavari, V., Credit risk assessment of borrowing companies from
  the bank using fuzzy hierarchical analysis and high grade neural network, International Journal
  of Industrial Engineering and Production Management, 2012, 23(1), P. 44-54.

 

• Bayazidi, F., Mohamadi, E., Mohamadi, M., Credit ranking of the real customers of the Mellat bank using data mining methods, First National Conference on Development of Monetary and Bank Management, Tehran, Permanent Secretariat of Monetary and Bank Management Conference, 2013.

 

• Cantú-Paz, E., Kamath, C., Combining evolutionary algorithms with oblique decision trees to detect bent-double galaxies, In Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation III, 2000, 4120, P. 63-71. Doi: 10.1117/12.403609.

 

• Tang, L., Cai. F., Ouyang, Y., Applying a nonparametric random forest algorithm to assess the credit risk of the energy industry in China, Technological Forecasting and Social Change, 2019, 144, P. 563-72.

 Doi: org/10.1016/j.techfore.2018.03.007.

 

• Abbasi Astamal M., Rahimi R., Designing an Expert System for Credit Rating of Real Customers of Banks Using Fuzzy Neural Networks, Advances in Mathematical Finance and Applications, 2019, 4(1), P. 89-102. Doi: 10.22034/amfa.2019.577561.1128.

 

• M., Improving the Banks Shareholder Long Term Values by Using Data Envelopment Analysis Model,Advances in Mathematical Finance and Applications, 2018,3(2), P.27-41.

        Doi:10.22034/AMFA.2018.540829.

 

[41] Izadikhah, M. Financial Assessment of Banks and Financial Institutes in Stock Exchange by Means of an Enhanced Two stage DEA Model. Advances in Mathematical Finance and Applications, 2021, 6(2), P. 207-232. Doi: 10.22034/amfa.2020.1910507.1491

 

[42] Kalantari, N., Rahmatolah Mohammadi Pour, R., Seidi, A., Shiri, A., Azizkhani M., Fuzzy Goal Programming Model to Rolling Performance Based Budgeting by Productivity Approach (Case Study: Gas Refiner-ies in Iran, Advances in Mathematical Finance and Applications, 2018, 3(3), P. 95-107.

        Doi: 10.22034/AM FA.2018.544952.