Assessment of Customer Credit Risk using an Adaptive Neuro-Fuzzy System

Document Type : Machine learning-Sadoghi


1 rajaee teacher training university

2 Khajeh Nasir toosi university of technology


Given the financial crises in the world, one of the most important issues of banking industry is the assessment of customers' credit to distinguish bad credit customers from good credit customers. The problem of customer credit risk assessment is a binary classification problem, which suffers from the lack of data and sophisticated features as main challenges. In this paper, an adaptive neuro-fuzzy inference system is exploited to tackle the customer credit risk assessment problem regarding the mentioned challenges. First of all, a SOMTE-based algorithm is introduced to overcome the data imbalancing problem. Then, several efficient features are identified using a MEMETIC meta-heuristic algorithm, and finally an adaptive neuro-fuzzy system is exploited for distinguishing bad credit customers from good ones. To evaluate and compare the performance of the proposed system, the standard German credit data dataset and the well-known classification algorithms are utilized. The results indicate the superiority of the proposed system compared to some well-known algorithms in terms of precision, accuracy, and Type II errors.


[1] S. Akkoç, "An empirical comparison of conventional techniques, neural networks and the three stage hybrid Adaptive Neuro Fuzzy Inference System (ANFIS) model for credit scoring analysis: The case of Turkish credit card data," European Journal of Operational Research, Vol. 222, No.1, pp. 168-178, (2012).
[2] P. Danenas, G. Garsva, and S. Gudas, "Credit risk evaluation model development using support vector based classifiers," Procedia Computer Science, Vol. 4, No.2, pp. 1699-1707, (2011).
[3] S. Finlay, "Multiple classifier architectures and their application to credit risk assessment," European Journal of Operational Research, vol. 210, No.4, pp. 368-378, (2011).
[4] X. Li, N. Xiao, C. Claramunt, and H. Lin, "Initialization strategies to enhancing the performance of geneticalgorithms for the p-median problem," Computers & Industrial Engineering, Vol. 61, No.2, pp. 1024-1034, (2011).
[5] L. Yu, S. Wang, and K. K. Lai, "An intelligent-agent-based fuzzy group decision making model for financial multicriteria decision support: The caseof credit scoring," European journal of operational research, Vol. 195, No.4, pp. 942-959, (2009).
[6] K. K. Lai, L. Yu, S. Wang, and L. Zhou, "Credit risk analysis using a reliability-based neural network ensemble model," in International Conference on Artificial Neural Networks, pp. 682-690, (2006).
[7] K. K. Lai, L. Yu, S. Wang, and L. Zhou, "Neural network metalearning for credit scoring," in International Conference on Intelligent Computing, , pp. 403-408, (2006).
[8] K. K. Lai, L. Yu, L. Zhou, and S. Wang, "Credit risk evaluation with least square support vector machine," in International Conference on Rough Sets and Knowledge Technology, pp. 490-495. (2006).
[9] Y. Wang, S. Wang, and K. K. Lai, "A new fuzzy support vector machine to evaluate credit risk," IEEE Transactions on Fuzzy Systems, Vol. 13, No.4, pp. 820-831, (2005).
[10] R. A. Fisher, "The use of multiple measurements in taxonomic problems," Annals of human genetics, Vol. 7, No.6, pp. 179-188, (1936).
[11] J. C. Wiginton, "A note on the comparison of logit and discriminant models of consumer credit behavior," Journal of Financial and Quantitative Analysis, Vol. 15, No.2, pp. 757-770, (1980).
[12] B. J. Grablowsky and W. K. Talley, "Probit and discriminant functions for classifying credit applicants-a comparison," Journal of Economics and Business, Vol. 33, No.2, pp. 254-261, (1981).
[13] F. Glover, "Improved linear programming models for discriminant analysis," Decision sciences, Vol. 21, No.3, pp. 771-785, (1990).
[14] O. L. Mangasarian, "Linear and nonlinear separation of patterns by linearprogramming," Operations Research, Vol. 13, No.3, pp. 444-452, (1965).
[15] M. Šušteršič, D. Mramor, and J. Zupan, "Consumer credit scoring models with limited data," Expert Systems with Applications, Vol. 36, No.1, pp. 4736-4744, (2009.
[16] R. Malhotra and D. K. Malhotra, "Evaluating consumer loans using neural networks," Omega, Vol. 31, No.3, pp. 83-96, (2003).
[17] M. C. Chen and S. H. Huang, "Credit scoring and rejected instances reassigning through evolutionary computation techniques," Expert Systems with Applications, Vol. 24, No.3, pp. 433-441, (2003).
[18] Q. Gu, Z. Cai, and L. Zhu, "Classification of imbalanced data sets by using the hybrid re-sampling algorithm based on isomap," in International Symposium on Intelligence Computation and Applications, pp. 287-296. (2009).
[19] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic minority over-sampling technique," Journal of Artificial Intelligence Research, Vol. 16, No.1, pp. 321-357, (2002).
[20] T. Maciejewski and J. Stefanowski, "Local neighbourhood extension of SMOTE for mining imbalanced data," in Computational Intelligence and Data Mining (CIDM), 2011 IEEE Symposium on, pp. 104-111, (2011).
[21] K. Gao, T. M. Khoshgoftaar, and A. Napolitano, "Combining Feature Subset Selection and Data Sampling for Coping with Highly Imbalanced Software Data," in SEKE, pp. 439-444, (2015).
[22] J. Eggermont, J. N. Kok, and W. A. Kosters, "Genetic programming for data classification: Partitioning the search space," in Proceedings of the 2004 ACM symposium on Applied computing, pp. 1001-1005,(2004).
[23] L. Yu, S. Wang, and K. K. Lai, "Credit risk assessment with a multistage neural network ensemble learning approach," Expert systems with applications, Vol. 34, No.3, pp. 1434-1444, (2008).
[24] J. Kruppa, A. Schwarz, G. Arminger, andA. Ziegler, "Consumer credit risk: Individual probability estimates using machine learning," Expert Systems with Applications, Vol. 40, No.1, pp. 5125-5131, (2013).
[25] S. Oreski and G. Oreski, "Genetic algorithm-based heuristic for feature selection in creditrisk assessment," Expert systems with applications, Vol. 41, No.4, pp. 2052-2064, (2014).
[26] N. Mohammadi and M. Zangeneh, "Customer Credit Risk Assessment using Artificial Neural Networks," IJ Information Technology and Computer Science, Vol. 8, No.2, pp. 58-66, (2016).
[27] E. K. Burke, J. P. Newall, and R. F. Weare, "A memetic algorithm for university exam timetabling," in International Conference on the Practice and Theory of Automated Timetabling, pp. 241-250,(1995).
[28] D. Liu, K. C. Tan, C. K. Goh, and W. K. Ho, "A multiobjective memetic algorithm based on particle swarm optimization," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol. 37, No.2, pp. 42-50, (2007).
[29] L. A. Zadeh, "Fuzzy sets and information granularity," in Fuzzy Sets, Fuzzy Logic, And Fuzzy Systems: Selected Papers by Lotfi A Zadeh, ed: World Scientific, pp. 433-448, (1996).
[30] S. H. Chen, Y. H. Lin, L. C. Chang, and F. J. Chang, "The strategy of building a flood forecast model by neuro‐fuzzy network," Hydrological Processes: An International Journal, Vol. 20, No.3, pp. 1525-1540, (2006).
[31] S. Farzi, H. Faili, and S. Kianian, "A preordering model based on phrasal dependency tree," Digital Scholarship in the Humanities, (2018).
[32] M. Firat and M. Güngör, "River flow estimation using adaptive neuro fuzzy inference system," Mathematics and Computers in Simulation, Vol. 75, No.1, pp. 87-96, (2007).
[33] M. Firat and M. E. Turan, "Monthly river flow forecasting by an adaptive neuro‐fuzzy inference system," Water and Environment Journal, Vol. 2, No.2 pp. 116-125, (2010).
[34] P. Nayak, K. Sudheer, and K. Ramasastri, "Fuzzy computing based rainfall–runoff model for real time flood forecasting," Hydrological Processes: An International Journal, Vol. 19, No.2, pp. 955-968, (2005.
[35] P. C. Nayak, K. Sudheer, D. Rangan, and K. Ramasastri, "A neuro-fuzzy computing technique for modeling hydrological time series," Journal of Hydrology, Vol. 291, No.4, pp. 52-66, (2004.
[36] K.-J. Wang, B. Makond, K.-H. Chen, and K.-M. Wang, "A hybrid classifier combining SMOTE withPSO to estimate 5-year survivability of breast cancer patients," Applied Soft Computing, Vol. 20, No.2, pp. 15-24, (2014).