A Machine Learning Model for Accurate Credit Risk Forecasting in Banking Systems: An Empirical Investigation

Document Type : TORS 2022

Authors

1 Optimisation et Analyse des Systèmes Industriels et de Service Ecole Nationale d’Ingénieurs de Tunis Laboratoire Génie Industriel

2 Ecole Nationale d'Ingénieurs de Carthage

3 kedge business school

4 Ecole Nationale d’Ingénieurs de Tunis Laboratoire Génie Industriel Centrale Supelec, University of Paris Saclay Paris, France

Abstract

Credit risk consists is the expectation of losses stemming from the inability of a borrower to repay a loan. For the purpose of accurate control of credit risks, banking systems seek developing financial information portfolios upon their customers using sophisticated models which are not only restricted to collecting information on borrower’s characteristics, but also, provide visibility on their respective default risk. This paper introduces a novel deep learning model to forecast the credit risk of company customers in banking systems. In particular, we develop a hybrid SVM-LSTM based neural network that predicts the total turnover of a company given the historical data records of its economic and financial features within specific periods. Through an empirical investigation based on data of 13 Tunisian manufacturing and service companies, we show that our proposed model results in more accurate statistical performances compared to the standard LSTM and to the linear regression that is commonly used in the area of credit risk management.

Keywords

References

Abdesslem, R. B., Chkir, I., & Dabbou, H. (2022). Is managerial ability a moderator? The effect of credit risk and liquidity risk on the likelihood of bank default. International Review of Financial Analysis, 80, 102044.
Alalshekmubarak, A., Smith, L. S. (2013, March). A novel approach combining recurrent neural network and support vector machines for time series classification. In 2013 9th International Conference on Innovations in Information Technology (IIT) (pp. 42-47). IEEE.
Ala’raj, M., Abbod, M. F., & Majdalawieh, M. (2021). Modelling customers credit card behaviour using bidirectional LSTM neural networks. Journal of Big Data, 8(1), 1-27.
Alfian, G., Syafrudin, M., Fahrurrozi, I., Fitriyani, N. L., Atmaji, F. T. D., Widodo, T., ... & Rhee, J. (2022). Predicting breast cancer from risk factors using SVM and extra-trees-based feature selection method. Computers, 11(9), 136.
Altan, A., & Karasu, S. (2019). The effect of kernel values in support vector machine to forecasting performance of financial time series. The Journal of Cognitive Systems, 4(1), 17-21.
Babu, N. R., and Mohan, B. J. (2017). Fault classification in power systems using EMD and SVM. Ain Shams Engineering Journal, 8(2), 103-111.
Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PloS one, 12(7), e0180944.
Barboza, F., Kimura, H., Sobreiro, V. A., Basso, L. F. (2016). Credit risk: from a systematic literature review to future directions. Corporate Ownership & Control, 13(3), 326-346.
Bhatore, S., Mohan, L., & Reddy, Y. R. (2020). Machine learning techniques for credit risk evaluation: a systematic literature review. Journal of Banking and Financial Technology, 4, 111-138.
Chaabane, S. B., Hijji, M., Harrabi, R., & Seddik, H. (2022). Face recognition based on statistical features and SVM classifier. Multimedia Tools and Applications, 81(6), 8767-8784.
Chandra, M. A., and Bedi, S. S. (2021). Survey on SVM and their application in image classification. International Journal of Information Technology, 13, 1-11.
Cuentas, S., Garcia, E., & Penabaena-Niebles, R. (2022). An SVM-GA based monitoring system for pattern recognition of autocorrelated processes. Soft Computing, 26(11), 5159-5178.
Festinger, L., Carlsmith, J. M. (1959). Cognitive consequences of forced compliance. The journal of abnormal and social psychology, 58(2), 203.
Hasni, M. and Bhar Layeb, S. (2017). Multiple regression-based models for accurate credit risk management, International Journal of Economics & Strategic Management of Business Process (Special Issue: The 5th International Conference on Innovation & Engineering - IEM2017), volume 10, Issue 1, pages 53-57.
Htun, H. H., Biehl, M., & Petkov, N. (2023). Survey of feature selection and extraction techniques for stock market prediction. Financial Innovation, 9(1), 26.
Huang, X., Liu, X., & Ren, Y. (2018). Enterprise credit risk evaluation based on neural network algorithm. Cognitive Systems Research, 52, 317-324.
Jiang, J., Chen, R., Chen, M., Wang, W., & Zhang, C. (2019). Dynamic fault prediction of power transformers based on hidden Markov model of dissolved gases analysis. IEEE Transactions on Power Delivery, 34(4), 1393-1400.
Jiang, H., Ching, W. K., Yiu, K. F. C., and Qiu, Y. (2018). Stationary Mahalanobis kernel SVM for credit risk evaluation. Applied Soft Computing, 71, 407-417.
Jiang, P., Huang, Y., and Liu, X. (2021). Intermittent demand forecasting for spare parts in the heavy-duty vehicle industry: a support vector machine method. International Journal of Production Research, 59(24), 7423-7440.
Kaldor, N. (1971). Conflicts in national economic objectives. The Economic Journal, 81(321), 1-16.
Kanapickiene, R., & Spicas, R. (2019). Credit risk assessment model for small and micro-enterprises: The case of Lithuania. Risks, 7(2), 67.
Kurani, A., Doshi, P., Vakharia, A., & Shah, M. (2023). A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting. Annals of Data Science, 10(1), 183-208.
Li, W., Paraschiv, F., & Sermpinis, G. (2022). A data-driven explainable case-based reasoning approach for financial risk detection. Quantitative Finance, 22(12), 2257-2274.
Li, Y., Li, Y., and Li, Y. (2019). What factors are influencing credit card customer’s default behavior in China? A study based on survival analysis. Physica A: Statistical Mechanics and its Applications, 526, 120861.
Lin, J., and Han, L. (2021). Lattice clustering and its application in credit risk management of commercial banks. Procedia Computer Science, 183, 145-151.
Lin, Z., Feng, M., Santos, C. N. D., Yu, M., Xiang, B., Zhou, B., & Bengio, Y. (2017). A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130.
Liu, M., Wang, M., Wang, J., & Li, D. (2013). Comparison of random forest, support vector machine and back propagation neural network for electronic tongue data classification: Application to the recognition of orange beverage and Chinese vinegar. Sensors and Actuators B: Chemical, 177, 970-980.
Liu, Q., Tan, T., & Yu, K. (2016, November). An investigation on deep learning with beta stabilizer. In 2016 IEEE 13th International Conference on Signal Processing (ICSP) (pp. 557-561). IEEE.
Lolli, F., Gamberini, R., Regattieri, A., Balugani, E., Gatos, T., Gucci, S. (2017). Single-hidden layer neural networks for forecasting intermittent demand. International Journal of Production Economics, 183, 116-128.
Maleki, M. S., Motevallian, S. N., Hosseini, F., Sabokrou, M., & Maleki, H. S. (2021, October). Improvement of credit scoring by lstm autoencoder model. In 2021 11th International Conference on Computer Engineering and Knowledge (ICCKE) (pp. 182-187). IEEE.
Narayan, Y., Ahlawat, V., & Kumar, S. (2020). Pattern recognition of sEMG signals using DWT based feature and SVM Classifier. International Journal of Advance and Science Technology, 29(10), 2243-2256.
Pang, S., Hou, X., and Xia, L. (2021). Borrowers’ credit quality scoring model and applications, with default discriminant analysis based on the extreme learning machine. Technological Forecasting and Social Change, 165, 120462.
Pascanu, R., Gulcehre, C., Cho, K., and Bengio, Y. (2013). How to construct deep recurrent neural networks. arXiv preprint arXiv:1312.6026.
Qi, P., Wang, F., Huang, Y., and Yang, X. (2022). Integrating functional data analysis with case-based reasoning for hypertension prognosis and diagnosis based on real-world electronic health records. BMC Medical Informatics and Decision Making, 22(1), 149.
Seong-Uk Nam, Sangil Kim, HyunMin Kim, and YongBin Yu. (2021). Comparative study of the performance of support vector machines with various kernels. East Asian Mathematical Journal, 37(3), 333-354.
Su, C. W., Cai, X. Y., Qin, M., Tao, R., & Umar, M. (2021). Can bank credit withstand falling house price in China? International Review of Economics & Finance, 71, 257-267.
Sun, J., Lang, J., Fujita, H., & Li, H. (2018). Imbalanced enterprise credit evaluation with DTE-SBD: Decision tree ensemble based on SMOTE and bagging with differentiated sampling rates. Information Sciences, 425, 76-91.
Tam, K. Y., Kiang, M. Y. (1992). Managerial applications of neural networks: the case of bank failure predictions. Management science, 38(7), 926-947.
Tang, Y., Song, Z., Zhu, Y., Yuan, H., Hou, M., Ji, J., ... & Li, J. (2022). A survey on machine learning models for financial time series forecasting. Neurocomputing, 512, 363-380.
Tian, Z., Xiao, J., Feng, H., & Wei, Y. (2020). Credit risk assessment based on gradient boosting decision tree. Procedia Computer Science, 174, 150-160.
Vu, M. T., Jardani, A., Krimissa, M., Zaoui, F., & Massei, N. (2023). Large-scale seasonal forecasts of river discharge by coupling local and global datasets with a stacked neural network: Case for the Loire River system. Science of The Total Environment, 165494.
Wang, C., Han, D., Liu, Q., Luo, S. (2018). A deep learning approach for credit scoring of peer-to-peer lending using attention mechanism LSTM. IEEE Access, 7, 2161-2168.
Wang, H., Zhang, F., Hou, M., Xie, X., Guo, M., & Liu, Q. (2018, February). Shine: Signed heterogeneous information network embedding for sentiment link prediction. In Proceedings of the eleventh ACM international conference on web search and data mining (pp. 592-600).
Worku, Y. B., & Muchie, M. (2019). The Uptake of E-Commerce Services in Johannesburg. Civil Engineering Journal, 5(2), 349-362.
Wu, Y., Xu, Y., & Li, J. (2019). Feature construction for fraudulent credit card cash-out detection. Decision Support Systems, 127, 113155.
Xia, Y., Li, Y., He, L., Xu, Y., & Meng, Y. (2021). Incorporating multilevel macroeconomic variables into credit scoring for online consumer lending. Electronic Commerce Research and Applications, 49, 101095.
Xiao, C., Xia, W., & Jiang, J. (2020). Stock price forecast based on combined model of ARI-MA-LS-SVM. Neural Computing and Applications, 32, 5379-5388.
Yang, L., & Shami, A. (2020). On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 415, 295-316.
International Journal of Supply and Operations Management
Volume 11, Issue 2
May 2024
Pages 168-187

Files

Share

How to cite

Statistics