Loan Evaluation Applying Artificial Neural Networks

ABSTRACT

The research presented pertains to the evaluation of loans' performance, using soft computing techniques and more specifically Artificial Neural Networks (ANN). Given the economic situation in Europe in the last few years, it is very important for the banks to assess credit risk deriving from loans. An example on consumer loans is presented, since management of retail exposures entails issues of everyday life being widely understood. Meanwhile the uncertainty on the risk that a Credit Institution bears when granting a loan to a customer with no prior performance history, is highlighted. Consequently, there is a variety of models that try to assess the probability of default of a loan, i.e. capital or interest not to be repaid. The model proposed in this study, has been trained with real historic data on clients' behavior and assets and can finally predict non-performing loans. A feedforward ANN has been created, which with simulation on unknown data for the network, managed to predict a quite satisfactory percentage, taking into consideration human parameters that influence these problems. It is remarkable that the proposed model is a rather useful tool that can support the judgment and final decision of loan officers and even replace empirical evaluation models.

References

1. Bojadziev, G., and Bojadziev, M. 2007. Fuzzy Logic for Business, Finance and Management, 2nd ed., vol. 23, Singapore: World Scientific.
2. Serguieva, A., and Hunter, J. 2004. Fuzzy interval methods in investment risk appraisal. Fuzzy Sets and Systems 142, 443--466.
3. Cheng, C.-H., Wei, L.-Y., Liu, J.-W., and Chen, T.-L. 2013. OWA-based ANFIS model for TAIEX forecasting. Economic Modelling 30, 442--448.
4. Wei, L.-Y. 2013. A GA-weighted ANFIS model based on multiple stock market volatility causality for TAIEX forecasting. Applied Soft Computing 13, 911--920.
5. Atsalakis, G., Dimitrakakis, E., and Zopounidis, C. 2011. Elliott Wave Theory and neuro-fuzzy systems, in stock market prediction: The WASP system. Expert Systems with Applications 38, 9196--9206.
6. Svalina, I., Galzina, V., Lujic, R., and Šimunovic, G. 2013. An adaptive network-based fuzzy inference system (ANFIS) for the forecasting: The case of close price indices. Expert Systems with Applications 40, 6055--6063.
7. Bagheri, A., Peyhani, H.M., and Akbari, M. 2014. Financial forecasting using ANFIS networks with Quantum-behaved Particle Swarm Optimization. Expert Systems with Applications 41, 6235--6250.
8. Huang, Z., Chen, H, Hsu, C.-J., Chen, W.-H, and Wu, S. 2004. Credit rating analysis with support vector machines and neural networks: a market comparative study. Decision Support Systems 37, 543--558.
9. Vanstone, B., and Finnie, G. 2010. Enhancing stockmarket trading performance with ANNs. Expert Systems with Applications 37, 6602--6610.
10. Choudhry, T., McGroarty, F., Peng, K., and Wang, S. 2012. High-frequency exchange rate prediction with an artificial neural network. Intelligent Systems in Accounting, Finance and Management 19, 170--178.
11. Kim, J.W. 1993. Expert systems for bond rating: a comparative analysis of statistical, rule-based and neural network systems, Expert Systems 10, 167--171.
12. Betz, F., Oprică, S., Peltonen, T.A., and Sarlin, P. 2014. Predicting distress in European banks. Journal of Banking & Finance 45, 225--241.
13. Tam, K., and Kiang M. 1992. Managerial application of neural networks: the case of bank failure predictions. Management Science 38(7), 926--947.
14. Wilson, R.L. and Sharda, S.R. 1994. Bankruptcy prediction using neural networks. Decision Support Systems 11(5), 545--557.
15. Kun, C.L., Ingoo, H., and Youngsig, K. 1996. Hybrid neural network models for bankruptcy predictions. Decision Support Systems 18(1), 63--72.
16. Glorfeld, L.W., and Hardgrave, B.C. 1996. An improved method for developing neural networks: The case of evaluating commercial loan creditworthiness. Computer Operation Research 23(10), 933--944.
17. Malhotra, R., and Malhotra, D.K. 2003. Evaluating consumer loans using neural networks. Omega 31(2), 83--96.
18. Haykin, S. 1999. Neural networks, a comprehensive foundation, 2nd ed., New Jersey: Prentice Hall.
19. Demuth, H., and Beale, M. 2001. Neural networks toolbox for use with Matlab, User's guide, The MathWorks, Inc.
20. Anderson, J.A. 1995. An introduction to neural networks, Branford Book.
21. UCI Machine Learning Repository http://archive.ics.uci.edu/ml/datasets/Statlog+(German+Credit+Data), accessed on March 10th 2016.