Contact Us Search Paper

Artificial neural network and Bayesian network models for credit risk prediction

Germanno Teles1, Joel J. P. C. Rodrigues1,2,3,*, Ricardo A. L. Rabê2, Sergei A. Kozlov3

Corresponding Author:

Joel J. P. C. Rodrigues


1. Instituto de Telecomunicações, Universidade da Beira Interior, Covilhã 6201-001, Portugal

2. Centro de Tecnologia, Federal University of Piau\'i (UFPI), Teresina -- PI 64049550, Brazil

3. Photonics and Optoinformatics Department, ITMO University, St. Petersburg 197101, Russia


Credit risk threatens financial institutions and may result in irrecoverable consequences. Tools for risk prediction can be used to reduce bank insolvency. This study compares Bayesian networks with artificial neural networks (ANNs) for predicting recovered value in a credit operation. The credit scoring problem is typically been approached as a supervised classification problem in machine learning. The present study explores this problem and finds that ANNs are a more efficient tool for predicting credit risk than the a¨ıve bayesian (NB) approach. The most crucial point is related to lending decisions, and a significant credit operation is associated with a set of factors to the degree that probabilities are used to classify new applicants based on their characteristics. The optimum achievement was obtained when the linear regression was equivalent to 0.2, with a mean accuracy of 85%. For the na¨ıve Bayes approach, the algorithm was applied to four datasets in a single process before the entire dataset was used to create a confusion matrix.


Artificial intelligence, Neural network, Bayesian network, Algorithms, Credit risk, Prediction

Downloads: 191 Views: 796
Cite This Paper:

Germanno Teles, Joel J. P. C. Rodrigues, Ricardo A. L. Rabê, Sergei A. Kozlov (2020). Artificial neural network and Bayesian network models for credit risk prediction. Journal of Artificial Intelligence and Systems, 2, 118–132.


[1] Edward I Altman. Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy. The Journal of Finance, 23(4):589–609, 1968.
[2] A. C. Antonakis and M. E. Sfakianakis. Assessing naıve Bayes as a method for screening credit applicants. Journal of Applied Statistics, 36(5):537–545, 2009.
[3] Amir F. Atiya. Bankruptcy prediction for credit risk using neural networks: A survey and new results. IEEE Transactions on Neural Networks, 12(4):929–935, 2001.
[4] B Baesens, T Van Gestel, S Viaene, M Stepanova, J Suykens, and J Vanthienen. Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society, 54(6):627–635, jun 2015.
[5] Alireza Baghban, Ali Jalali, Mojtaba Shafiee, Mohammad Hossein Ahmadi, and Kwok-wing Chau. Developing an ANFIS-based swarm concept model for estimating the relative viscosity of nanofluids. Engineering Applications of Computational Fluid Mechanics, 13(1):26–39, 2019.
[6] William H. Beaver. Financial Ratios As Predictors of Failure. Journal of Accounting Research, 4:71–111, 1966.
[7] Berk Bekiroglu, Hidayet Takci, and Utku Can Ekinci. Bank Credit Risk Analysis With Bayesian Network Decision. IJAEST - INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES, 9(2):273–279, 2011.
[8] Leopold A. Bernstein. Financial statement analysis : theory, application, and interpretation. Irwin, 1993.
[9] Klaus Bocker. Rethinking Risk Measurement and Reporting, volume II. Risk Books, London, 2010.
[10] Andrew P. Bradley. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 30(7):1145–1159, jul 1997.
[11] Xinying Zhang Chong Wu, Yingjian Guo and Han Xia. Study of Personal Credit Risk Assessment Based on Support Vector Machine Ensemble. International Journal of Innovative Computing, Information and Control, 6(5):2353–2360, 2010.
[12] R. H. DAVIS, D. B. EDELMAN, and A. J. GAMMERMAN. Machine-learning algorithms for credit-card applications. IMA Journal of Management Mathematics, 4(1):43–51, 1992.
[13] N Davutyan and S Ozar. A credit scoring model for Turkey’s micro & small enterprises (MSE’s). In 13th Annual ERF Conference, pages 16–18, Kuwait, 2006.
[14] Peter R. Demerjian. Financial Ratios and Credit Risk: The Selection of Financial Ratio Covenants in Debt Contracts. AAA 2007 Financial Accounting & Reporting Section (FARS), 2007.
[15] Vijay S. Desai, Jonathan N. Crook, and George A. Overstreet. A comparison of neural networks and linear scoring models in the credit union environment. European Journal of Operational Research, 95(1):24–37, nov 1996.
[16] Douglas Diamond. Financial intermediation and delegated monitoring. Review of Economic Studies, 51(3):393–414, 1984.
[17] Ilia D. Dichev and Douglas J. Skinner. Large-sample evidence on the debt covenant hypothesis. Journal of Accounting Research, 40(4):1091–1123, 2002.
[18] Alaa El-Shazly. Financial Distress and Early Warning Signals: A Non-Parametric Approach with Application to Egypt. In 9th Annual Conference of the Economic Research Forum, number October, pages 1–25, Emirates, 2002.
[19] D J Hand and W E Henley. Statistical Classification Methods in Consumer Credit Scoring: a Review. Royal Statistical Society, pages 523–541, 1997.
[20] James A Hanley and Barbara J McNeil. The Meaning and Use of the Area under a Receiver Operating ( ROC ) Curvel Characteristic. Radiology, 143(1):29–36, 1982.
[21] Martin F Hellwig. Risk aversion and incentive compatibility with ex post information asymmetry. Journal of Economic Literature, 438:1–25, 1998.
[22] Jih Jeng Huang, Gwo Hshiung Tzeng, and Chorng Shyong Ong. Two-stage genetic programming (2SGP) for the credit scoring model. Applied Mathematics and Computation, 174(2):1039–1053, mar 2006.
[23] Huseyin Ince and Bora Aktan. A comparison of data mining techniques for credit scoring in banking: A managerial perspective. Journal of Business Economics and Management, 10(February 2015):233–240, 2009.
[24] Michael Jacobs and Nicholas M Kiefer. The Bayesian approach to default risk: A guide. Center for Analytical Economics, (March 2010), 2013.
[25] Vita Jagric, Davorin Kracun, and Timotej Jagric. Does non-linearity matter in retail credit risk modeling? Finance a Uver - Czech Journal of Economics and Finance, 61(4):384–402, 2011.
[26] Liu Jie and Song Bo. Naive Bayesian Classifier Based on Genetic Simulated Annealing Algorithm. Procedia Engineering, 23:504–509, jan 2011.
[27] J. W. Kay and D. M. Titterington. Statistics and Neural Networks Advance at the Interface. Oxford University Press, 2000.
[28] Amir E. Khandani, Adlar J. Kim, and Andrew W. Lo. Consumer credit-risk models via machine-learning algorithms. Journal of Banking & Finance, 34(11):2767–2787, nov 2010.
[29] Adnan Khashman. Neural networks for credit risk evaluation: Investigation of different neural models and learning schemes. Expert Systems with Applications, 37(9):6233–6239, 2010.
[30] HC Koh, WC Tan, and CP Goh. A two-step method to construct credit scoring models with data mining techniques. International Journal of Business . . . , 1(1):96–118, 2006.
[31] K Komorad. On credit scoring estimation. PhD thesis, Humboldt University, 2002.
[32] Adel Lahsasna, Raja Noor Ainon, and Teh Ying Wah. Credit scoring models using soft computing methods: A survey. The International Arab Journal of Information Technology, 7(2):115–123, 2010.
[33] Tian-Shyug Lee and I-Fei Chen. A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines. Expert Systems with Applications, 28(4):743–752, may 2005.
[34] Pawel Lewicki and Thomas Hill. Statistics : Methods and Applications, volume 1st. 2006.
[35] Russell James Lundholm and Richard G. Sloan. Equity valuation and analysis.
[36] Dominik Maltritz and Alexander Molchanov. Economic Determinants of Country Credit Risk: A Bayesian Approach. In 12th New Zealand Finance Colloquium, 2008.
[37] D. Martens, B.B. Baesens, and T. Van Gestel. Decompositional Rule Extraction from Support Vector Machines by Active Learning. IEEE Transactions on Knowledge and Data Engineering, 21(2):178–191, 2009.
[38] Khalil Masmoudi, Lobna Abid, and Afif Masmoudi. Credit risk modeling using Bayesian network with a latent variable. Expert Systems with Applications, 127:157–166, aug 2019.
[39] Hamadi Matoussi and Aida Krich`ene Abdelmoula. Credit-risk evaluation of a Tunisian commercial bank: logistic regression vs neural network modelling. International Journal of Accounting & Information Management, 19(2):ijaim.2011.36619baa.005, jun 2011.
[40] Ricardas Mileris. Estimation of loan applicants default probability applying discriminant analysis and simple Bayesian classifier. Economics and management, 15(1):1078–1084, 2010.
[41] Antonietta Mira and Paolo Tenconi. Bayesian estimate of credit risk via MCMC with delayed rejection. Stochastic Analysis, Random Fields and Applications IV, (January 2003):277–291, 2004.
[42] T M Mitchell. Generative and Discriminative Classifiers : Naive Bayes and Logistic Regression Learning Classifiers Based On Bayes Rule. In Machine Learning, page
432. McGraw-Hill Education, 2005.
[43] M.D. Odom and R. Sharda. A neural network model for bankruptcy prediction. 1990 IJCNN International Joint Conference on Neural Networks, pages 163–168 vol.2, 1990.
[44] James A. Ohlson. Financial Ratios and the Probabilistic Prediction of Bankruptcy. Journal of Accounting Research, 18(1):109, 1980.
[45] Krisna G. Palepu, Paul M. Healy, Victor L. Bernard, Sue Wright, Michael Bradbury, and Philip Lee. Business Analysis and Valuation Using Financial Statements. 2000.
[46] Belief Revision, Financial Distress, Sumit Sarkar, and Ram S. Sriram. Bayesian Models for Early Warning of Bank Failures. Management Science, 47(11):1457–1475, 2001.
[47] Bernard Rosner. Fundamentals of biostatistics. 2012.
[48] David E. Rumelhart and James L. McClelland. An interactive activation model of context effects in letter perception: II. The contextual enhancement effect and some tests and extensions of the model. Psychological Review, 89(1):60–94, 1982.
[49] Okan Veli Safakli. Credit Risk Assessment for the Banking Sector of Northern Cyprus. Banks and Bank System, 2:21, 2007.
[50] Clifford W. Smith and Jerold B. Warner. On financial contracting. An analysis of bond covenants. Journal of Financial Economics, 7(2):117–161, 1979.
[51] Neda Soltani Halvaiee and Mohammad Kazem Akbari. A novel model for credit card fraud detection using Artificial Immune Systems. Applied Soft Computing, 24:40–49, 2014.
[52] Kent A. Spackman. Signal detection theory: valuable tools for evaluating inductive learning. Proceeding Proceedings of the sixth international workshop on Machine learning, pages 160–163, 1989.
[53] A. Steenackers and M. J. Goovaerts. A credit scoring model for personal loans. Insurance Mathematics and Economics, 8(1):31–34, mar 1989.
[54] Thomas Stibor. A study of detecting computer viruses in real-infected files in the
n- gram representation with machine learning methods. 23rd International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, 6096 LNAI(PART 1):509–519, 2010.
[55] Lili Sun and Prakash P. Shenoy. Using Bayesian networks for bankruptcy prediction: Some methodological issues. European Journal of Operational Research, 180(2):738–753, jul 2007.
[56] Dennis Sweeney, David Anderson, and Thomas Williams. Statistics for Business and Economics. Thomson Learning EMEA, London, 7 edition, 2007.
[57] Anjan V Thakor. The Financial Crisis of 2007 – 2009 : Why Did It Happen and What Did We Learn ? Review of Corporate Finance Studies Advance Access, 4(2):1–51, 2015.
[58] Lyn C. Thomas, David B. Edelman, and Jonathan N. Crook. Credit Scoring and Its Applications. Society for Industrial and Applied Mathematics, jan 2002.
[59] Chih-Fong Tsai. Combining cluster analysis with classifier ensembles to predict financial distress. Information Fusion, 16:46–58, mar 2014.
[60] Gang Wang, Jinxing Hao, Jian Ma, and Hongbing Jiang. A comparative assessment of ensemble learning for credit scoring. Expert Systems with Applications, 38(1):223–230, jan 2011.
[61] David West, Scott Dellana, and Jingxia Qian. Neural network ensemble strategies for financial decision applications. Computers & Operations Research, 32(10):2543–2559, oct 2005.
[62] Dorota Witkowska, W Kaminski, Krzysztof Kompa, and Iwona Staniec. Neural networks as a supporting tool in credit granting procedure. Information Technology for Economics & Management, 2(1), 2004.
[63] Jiri Witzany. Credit Risk Management Pricing, Measurement, and Modeling. Springer, 2017.
[64] CL Wu and KW Chau. Rainfall–runoff modeling using artificial neural network coupled with singular spectrum analysis. Journal of Hydrology, 399(3-4):394–409, 2011.
[65] Bee Wah Yap, Seng Huat Ong, and Nor Huselina Mohamed Husain. Using data mining to improve assessment of credit worthiness via credit scoring models. Expert Systems with Applications, 38(10):13274–13283, sep 2011.
[66] Zaher Mundher Yaseen, Sadeq Oleiwi Sulaiman, Ravinesh C. Deo, and Kwok Wing Chau. An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction. Journal of Hydrology, 569(August 2018):387–408, 2019.
[67] Jozef Zurada, Niki Kunene, and Jian Guan. The Classification Performance of Multiple Methods and Datasets: Cases from the Loan Credit Scoring Domain. Journal of International Technology and Information Management, 23(1), 2014.