Kredi Skorunun Belirlenmesinde Yapay Sinir Ağları ve Karar Ağaçlarının Kullanımı Bir Model Önerisi

Abstract

Kredi riski bankacılıkta öne çıkan risklerden birisi olup bankaların karlılık oranlarını üzerinde önemli etkiye sahiptir. Buna bağlı olarak, bankalar ve diğer finans kuruluşları için tüketicilere kredi verme konusunda karar vermede yardımcı kredi skorlama sistemleri geliştirmek önem arz etmektedir. Finansal kuruluşlar, kredi/borç talep eden müşterilerine kredi kullandırma kararlarında izleyecekleri yolu belirleyebilmek için, kredi skoru üzerinde etkisinin olduğu düşünülen faktörler arası ilişkileri ortaya koyan çeşitli içsel kredi değerlendirme modellerine başvurmaktadır. Literatürde, kredi skorlaması analizlerinde istatistik ve makine öğrenme teknikleri yaygın olarak incelenmiştir. Bu çalışmada başta bankalar olmak üzere finansal kuruluşlar ve bu kuruluşların müşterileri için de önem arz eden müşteri kredi skorunun belirlenmesi konusu ele alınmaktadır. İstatistiksel teknikler ve makine öğrenme teknikleri, son yıllarda ticari kredilerindeki büyüme ile giderek daha önemli hale gelmiştir. İstatistiksel yöntemler geniş bir yelpazede uygulanmış olmasına rağmen ticari gizlilik nedeniyle literatürde sınırlı olarak yer almaktadır. Bu çalışmada, bir bankaya başvurarak kredi talep eden bireysel müşterilerin kredi talebinin kabul edilmesi ya da reddedilmesi kararının verilmesine yönelik, yapay sinir ağları (YSA) metodolojisini temel alan bir yazılım modeli önerilmektedir. Bir mevduat bankasına ait gerçek veri kümesi uygulamada kullanılmış ve sonuçları ayrıca geliştirilen karar ağacı (KA) modelinin sonuçları ile karşılaştırılmıştır. Her iki model doğrultusunda, bir bankaya gelen bireysel kredi başvurusuna yönelik verilecek nihai karar nümerik bir örnek üzerinden değerlendirilmektedir. Elde edilen bulgular, YSA modelinin müşteri kredi skorunun tespitinde yüksek öngörü doğruluğunu sağlama ve kredi riskini belirli ölçüde tahmin edebilmede KA modeline göre başarılı olduğunu göstermektedir. Bununla birlikte, geliştirilen yazılım modelinin kuruluşlara kredilerden elde ettikleri karlılık oranlarının artması hususunda da yararlı olacağı düşünülmektedir

Keywords

• Kredi riski, kredi değerliliği, kredi skoru, ticari banka, karar ağaçları, yapay sinir ağları

Using Artificial Neural Networks and Decision Trees for Credit Scoring: A Model Proposal

Abstract

Credit risk is one of the major risks faced by commercial banks and has an important effect on profitability ratios. Consequently, the credit scoring system in decision making for banks and other financial institutions lending to consumers is very important. Financial institutions constitute various internal credit assessment models reveal relationships between variables affecting credit scoring. In the literature, statistics and machine learning techniques for credit ratings have been widely studied. In this study, particularly for banks, financial institutions and customers of these institutions are discussed, including issues that are important to determine customer’s credit score. Customer’s credit score is a term used to allocate credit using statistical techniques and methods of machine learning techniques. Such methods have become increasingly more important in recent years with the growth in commercial loans. Although a wide range of applied statistical methods included in the literature, they are limited because of commercial confidentiality. In this study, for issuing the decision on the assessment of customers’ demand for credit, acceptance of loan requests or refusal, a software model based on the artificial neural network (ANN) methodology is recommended. A real data set belongs to a deposit bank was used for the application. In addition to this, this study benchmarks the performance of ANN model with decision trees (DT) model. Based on the findings, ANN model outperforms the DT model in terms of estimating credit risk and customer’s credit score. It is also considered that the model would be helpful in increasing the profitability of lenders gained from credits

Keywords

• Credit risk, credit worthiness, credit score, commercial banks, decision trees, neural networks

References

1. Abdou, H.A.(2009). Genetic programming for credit scoring: The case of Egyptian public sector banks, Expert Systems with Applications, 36 (9), s.11402-11417.
2. Anyaeche, C.O. ve Ighravwe, D.E.(2013). Predicting Performance Measures Using Linear Regression and Neural Network: A Comparison. African Journal of Engineering Research, 1(3), s.84-89.
3. Cao, L.(2003). Support Vector Machines Experts for Time Series Forecasting. Neurocomputing, 51, s.321-329.
4. Chen, M-Y.(2011). Predicting corporate financial distress based on integration of decision tree classification and logistic regression, Expert Systems with Applications, 38(9), s.11261-11272.
5. Chen, M-C., Huang, S-H.(2003). Credit scoring and rejected instances reassigning through evolutionary computation techniques, Expert Systems with Applications, 24 (4), s.433-441.
6. Chen, M-Y., Fan, M-H., Chen, Y-L. and Wei, H-M.(2013). Design of Experiments on Neural Network’s Parameters Optimization for Time Series Forecasting in Stock Markets, Neural Network World, 4(13), s.369-393.
7. Chen, S.,Goo, Y-J.J. and Shen, Z-D.(2014). A Hybrid Approach of Stepwise Regression, Logistic Regression, Support Vector Machine, and Decision Tree for Forecasting Fraudulent Financial Statements, 9(16), s.1-9.
8. Delen, D. Kuzey, C. and Uyar, A.(2013). Measuring firm performance using financial ratios: A decision tree approach, Expert Systems with Applications40(10), s.3970-3983.

9. Demuth, H., Beale, M. and Hagan, M.(2009). Neural Network Toolbox 6 User’s Guide. Natick, MA: The MathWorks, Inc.
10. D’Espallier, B., Guérin, I. and Mersland, R.(2009). Women and Repayment in Microfinance, Rural Microfinance and Employment, Working Paper 2009-2.
11. Giam, X., Olden, J.D.(2015). A new R2-based metric to shed greater insight on variable importance in artificial neural networks, Ecological Modelling, 313(10), s.307-313.
12. Giannetti, M., Burkart, M. ve Ellingsen, T.(2011). What You Sell Is What You Lend? Explaining Trade Credit Contracts. Rev. Financ. Stud., 24 (4), s. 1261-1298.
13. Hagan, M.M. ve Menhaj, M.B.(1999). Training Feed-Forward Networks with the Marquardt Algorithm. IEEE Transactions on Neural Networks, 6(5), s.989–991.
14. Han, Y. ve Wang, B.(2011). Investigation of Listed Companies Credit Risk Assessment Based on Different Learning Schemes of BP Neural Network. International Journal of Business and Management, 6(2), s.204-207.
15. Haykin, S.(2009). Neural Networks and Learning Machine, 3E. NJ: Pearson Education Inc.
16. Hippert, H.S., Pedreira, C.E. and Souza, R.C.(2001). Neural Networks for Short-Term Load Forecasting: A Review and Evaluation. IEEE Transactıons on Power Systems, 16(1), s.44-55.
17. Hsieh, N-C.(2005). Hybrid mining approach in the design of credit scoring models, Expert Systems with Applications, 28 (4), s. 655-665.
18. Hsieh, N-C.(2004). An integrated data mining and behavioral scoring model for analyzing bank customers, Expert Systems with Applications, 27 (4), s. 623-633.
19. Kim, H. S., & Sohn, S. Y.(2010). Support vector machines for default prediction of SMEs based on technology credit, European Journal of Operational Research, 201(3),s. 838–846.
20. Landajo M., Andrés, J., Lorca, P.(2007). Robust neural modeling for the cross-sectional analysis of accounting information, European Journal of Operational Research, 177 (2), s.1232-1252.
21. Lavanya, V. ve Parveentaj, M.(2013). Foreign Currency Exchange Rate (FOREX) Using Neural Network, International Journal of Science and Research, 2(10): s.174-177.
22. Lee, T-S., Chen, I-F.(2005). A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines, Expert Systems with Applications, 28 (4), s.743-752.
23. Lee, T-S., Chiu, C-C., Lu, C-J., ve Chen, I-F. (2002). Credit scoring using the hybrid neural discriminant technique, Expert Systems with Applications, 23 (3), s.245-254.
24. Lessmann, S.; Baesens, B.; Seow, H-V. ve Thomas, L.C.(2015). Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research, European Journal of Operational Research, 247 (1), s.124-136.
25. Makeig, S., Jung, T.P. ve Sejnowski, T.J..(1996). Using Feedforward Neural Networks to Monitor Alertness from Changes in EEG Correlation and Coherence, Advances in neural information processing systems. Cambridge: MIT Press, s.931–937.
26. Olson, D. ve Zobuni, T.(2011). Efficiency and Bank Profitability in MENA Countries, Emerging Markets Review, 12, s.104-110.
27. Olson, D., Delen, D. and Meng, Y.(2012) Comparative analysis of data mining methods for bankruptcy prediction, Decision Support Systems, 52(2), s.464-473.
28. Öztemel, E..(2012). Yapay Sinir Ağları. İstanbul: Papatya Yayıncılık.
29. Rani, M.S., Xavier, S.B.(2015). A Hybrid Intrusion Detection System Based on C5.0 Decision Tree Algorithm and One- Class SVM with CFA, International Journal of Innovative Research in Computer and Communication Engineering, s.5526-5537.
30. Ravi, V. ve Zimmermann, H.J.(2001). A Neural Network and Fuzzy Rule Base Hybrid for Pattern Classification, Soft Computing, 5(2), s.152–159.
31. Ritz, R. A., (2012). How do banks respond to increased funding uncertainty?, Cambridge Working Papers in Economics 1213, Faculty of Economics, University of Cambridge.
32. Sheen, J.N.(2005). Fuzzy financial profitability analyses of demand side management alternatives from participant perspective, Information Sciences, 169 (3), s. 329-364.
33. Tsai, C-F. and Chen, M-L. (2010). Credit rating by hybrid machine learning techniques, Applied Soft Computing, 10, s.374-380.
34. Washington, S. Karlaftis, M. ve Mannering, F..(2011). Statistical and Econometric Methods for Transportation Data Analysis - 2nd Edition, Boca Raton, FL: Chapman and Hall/CRC.
35. West, D.(2000). Neural network credit scoring models, Computers & Operations Research 27, s.1131-1152.
36. Yazıcı, M.(2011). Kredi Kartı Taleplerinin Değerlendirilmesinde Değişken Analizi, Maliye Finans Yazıları, s.9-22.