CREDIT RISK MODELLING FOR INDIAN DEBT SECURITIES USING MACHINE LEARNING
Abstract
We develop a new credit risk model for Indian debt securities rated by major credit rating agencies in India using the ordinal logistic regression (OLR). The robustness of the model is tested by comparing it with classical models available for ratings prediction. We improved the model’s accuracy by using machine learning techniques, such as the artificial neural networks (ANN), support vector machines (SVM) and random forest (RF). We found that the accuracy of our model has improved from 68% using OLR to 82% when using ANN and above 90% when using SVM and RF.
Downloads
References
Agresti, A. (2002). Categorical Data Analysis (2nd ed.). USA: Wiley Series in Probability and Statistics.
Alifiah, M. N., & Tahir, M. S. (2018). Predicting Financial Distress Companies in the Manufacturing and Non-Manufacturing Sectors in Malaysia Using Macroeconomic Variables. Management Science Letters, 8, 593-604.
Altman. (1968). Financial Ratios, Discriminant Analysis and the Prediction of Corporate. Journal of Finance, 23, 589-609.
Altman. (2005). An Emerging Market Scoring System for Corporate Bonds. Emerging Markets Review, 6, 311-323. https://doi.org/10.1016/j.ememar.2005.09.007
Altman, Haldeman, R. G., & P, N. (1977). Zeta Analysis: A New model to identify bankruptcy risk of corporations. Journal of banking and finance, 1, 29-54.
Altman, Hartzel, J., & Peck, M. (1998). Emerging Market Corporate Bonds - A Scoring System. Emerging Market Capital Flows, 2, 391-400. https://doi.org/10.1007/978-1-4615-6197-2_25
Ang, J. S., & Patel, K. A. (1974). Bond Rating Methods: Comparison and Validation. The Journal of Finance, 30, 631-640.
Back, B., Laitinen, T., & Sere, K. (1996). Neural Networks and Genetic Algorithms for Bankruptcy Predictions. Expert Systems with Applications, 11, 407-413. https://doi.org/10.1016/S0957-4174(96)00055-3
Bandyopadhyay, A. (2006, May). Predicting Probability of Default of Indian Corporate Bonds: Logistic and Z-Score Model Approaches. The Journal of Risk Finance, 7, 255-272. https://doi.org/0.1108/15265940610664942
Barboza, F., Kimura, H., & Altman, E. (2017). Machine Learning Models and Bankruptcy Prediction. Expert Systems With Applications, 83, 405-417. http://dx.doi.org/10.1016/j.eswa.2017.04.006
Basel. (2017). Basel III. Basel Committee of banking supervision. Retrieved from https://www.bis.org/
Beaver, W. H. (1966). Financial Ratios as Predictors of Failure. Journal of Accounting Research, 4, 77-111.
Benmelech, E., & Dlugosz, J. (2009). The Credit Rating Crisis. NBER Macroeconomics Annual, 24, 161-207.
Breiman, L. (2001). Random Forests. Machine Learning, 5-32.
Brooks, L. D., Ingram, R. W., & Copeland, R. M. (1983). Credit Risk, Beta, and Bond Ratings. Nebraska Journal of Economics and Business, 22, 3-14.
Cortes, C., & Vapnik, V. (1995). Support-Vector Networks. Machine Leaming, 273-297.
CRISIL. (2018). CRISIL Yearbook On The Indian Debt Market. CRISIL.
D.McFadden. (1974). Conditional logit analysis of qualitative choice behavior. Frontiers in Econometrics, 105-142.
D.R.Cox, & Snell, E. (1989). Analysis of Binary Data (2 ed.). Chapman & Hall.
Deakin, E. B. (1972). A Discriminant Analysis of Predictors of Business Failure. Journal of Accounting Research, 10, 167 - 179.
Duvall, R. M., & R.S.Rathinasamy. (1993). The Association of Default Risk Factors with Systematic Risk of Corporate Bonds. Journal of Economics and Finance, 17,137-147.
Emerson, S., Kennedy, R., O’Shea, L., & O’Brien, J. (2019). Trends and Applications of Machine Learning in Quantitative Finance. 8th International Conference on Economics and Finance Research. Retrieved from https://ssrn.com/abstract=3397005
Gante, D. D., Gerardo, B. D., & Tanguilig, B. T. (2015). Neural Network Model Using Backpropogaton Algorithm for Credit Risk Evaluation. 12–13. Penang. Malaysia: International Conference on Artificial Intelligence and Computer Science (AICS2015).
Gentry, J., Whitford, D., & Newbold, P. (1985). Predicting Industrial Bond Ratings with a Probit Model and Funds Flow Components. Bureau of Economic and Business Research, 46, 41-48. https://doi.org/10.2469/faj.v46.n4.41
Gerardi, K., Sherlund, S. M., Lehnert, A., & Willen, P. (2008). Making Sense of the Subprime Crisis. Brookings Papers on Economic Activity, 69-145.
Günther, F., & Fritsch, S. (2010). neuralnet: Training of Neural Networks. The R Journal, 2.
Ho, C., & Rao, R. P. (1993). Bond Ratings and Their Determinants in a Changing Environment. Journal of Applied Business Research, 9, 132-139. https://doi.org/10.19030/jabr.v9i1.6104
Horrigan, J. 0. (1966). The Determination of Long-Term Credit Standing With Financial Ratios. Journal of Accounting Research, 4, 44-62.
Hosmer, D. W., & Lemeshow, S. (2000). Applied Logistic Regression (2 ed.). Wiley-Interscience.
Huang, Z., Chen, H., Hsua, C.-J., Chen, W.-H., & Wu, S. (2004). Credit Rating Analysis with Support Vector Machines and Neural Networks: A Market Comparative Study. Decision Support Systems, 37, 543– 558. https://doi.org/10.1016/S0167-9236(03)00086-1
Ibourk, A., & Aazzab, A. (2016). The Artificial Neural Networks for Classification: Case of Business Failures. Journal of Research in Business and Management, 4,10-15.
Imdadullah, M., Aslam, M., & Altaf, S. (2016, Dec). mctest: An R Package for Detection of Collinearity among Regressors. The R Journal, 8.
Iturriaga, F. J., & Sanz, I. P. (2015). Bankruptcy Visualization and Prediction Using Neural Networks: A Study of U.S. Commercial Banks. Expert Systems with Applications, 42, 2857-2869. http://dx.doi.org/10.1016/j.eswa.2014.11.025
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An Introduction to Statistical Learning with Applications in R. New York: Springer.
Kaplan, R. S., & Urwitz, G. (1979, 1979). Statistical Models of Bond Ratings: A Methodological Inquiry. The Journal of Business, 52, 231-261.
Kohavi, R., & Provost, F. (1998). Glossary of Terms. Special Issue on Applications of Machine Learning and the Knowledge Discovery Process, 30, 271-274.
Labatut, V., & Cherifi, H. (2011). Evaluation of Performance Measures for Classifiers Comparison. Ubiquitous Computing and Communication Journal, 6, 21-34.
McCullagh., P. (1980). Regression Models for Ordinal Data. Journal of the Royal Statistical Society, 42, 109 - 142.
McCulloch, W. S., & Pitts, W. (1943). A Logical Calculus of the Ideas Immanent in Nervous Activity. The Bulletin of Mathematical Biophysics, 5, 115-143.
Mitrani, A. (2019). Evaluating Categorical Models II sensitivity and specificity. Toward Data Science. Retrieved from https://towardsdatascience.com/evaluating-categoricalmodels-ii-sensitivity-and-specificity-e181e573cff8.
Moody. (2000). Risckcalc for Private Companies: Moody’s Default Model. Moody’s investor service.
Nagelkerke, N. J. (1991). A Note on a General Definition of the Coefficient of Determination. Biometrika, 78, 691-692.
OGD, O. G. (2018). https://data.gov.in/.
Palande, P. (2015, November 23). Amtek Auto: The Silo effect. Forbes India.
Partnoy, F. (2009, April). Rethinking Regulation of Credit Rating Agencies: An Institutional Investor Perspective. The Council of Institutional Investors.
Pillay, A. (2015, Sep). Have Rating Agencies Been Caught Napping on Corporate Debt? Livemint. Retrieved from https://www.livemint.com/Companies/nKiB6RuSI5fXpvPVqxBr6H/Have-rating-agencies-been-caught-napping.html
Pinches, G. E., & Mingo, K. A. (1973, March). Multivariate Analysis of Industrial Bond Rating. Journal of Finance, 28, 1-18.
Pradhan, R. (2014). Z Score Estimation for Indian Banking Sector. International Journal of Trade, Economics and Finance, 5, 516-520. https://doi.org/10.7763/IJTEF.2014.V5.425
Pogue , T. F., & Soldofsky., R. M. (1969). What is in a Bond Rating. Journal of Financial and Quantitative Analysis, 4, 201-228.
SEBI. (2011, June 15). Standardisation of Rating Symbols and Definitions. India.
Sharma, S.S & Sha, Y. (2020) Part A: Special Section on COVID-19 Research. Emerging Markets Finance and Trade, 56, 3551-3553. https://doi.org/10.1080/1540496X.2020.1858617
Sha, Y., & Sharma, S. S. (2020). Research on Pandemics Special Issue of the Journal Emerging Markets Finance and Trade. Emerging Markets Finance and Trade, 56, 2133–2137. https://doi.org/10.1080/1540496x.2020.1795467
Venables, W. N., & Ripley, B. D. (2002). Modern Applied Statistics with S. Springer.
Wang, G., Mac, J., & Yang, S. (2014). An Improved Boosting Based on Feature Selection for Corporate Bankruptcy Prediction. Expert Systems with Applications, 41, 2353 - 2361.
Yeh, C.-C., Chi, D.-J., & Lin, Y.-R. (2014). Going-concern Prediction Using Hybrid Random Forests and Rough Set Approach. Information Sciences, 254, 98–110. https://doi.org/10.1016/j.ins.2013.07.011
Yim, J., & Mitchell, H. (2005). A Comparison Of Corporate Distress Prediction Models in Brazil: Hybrid Neural Networks, Logit Models and Discriminant Analysis. nova Economia, 15, 73-93.
Yuan, S., & Chu, F. (2007). Fault Diagnostics Based on Particle Swarm Optimization and Support Vector Machines. Mechanical Systems and Signal Processing, 21,1787-1798.
Zurada, J., Foster, B. P., & Ward, T. J. (2002). Investigation of Artificial Neural Networks for Classifying Levels of Financial Distress of Firms: The Case of an Unbalanced Training Sample. Knowledge Discovery for Business Information Systems, 600, 397-424.
Copyright (c) 2021 Buletin Ekonomi Moneter dan Perbankan
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Buletin Ekonomi Moneter dan Perbankan / Bulletin of Monetary Economics and Banking is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
