Forecasting Enterprises Bankruptcy by Extreme Gradient Boosting
DOI:
https://doi.org/10.14529/cmse200305Keywords:
extreme gradient boosting, bankruptcy, enterprises, synthetic minority oversampling techniqueAbstract
The application of models for forecasting bankruptcy of enterprises for controlling investment is the basis for monitoring activities of financial institutions. A crucial factor in allowing financial institutions to determine the amount of capital to cover credit losses is the accuracy of the forecast. Most studies use traditional statistical methods (for example, linear discriminant analysis and logistic regression) to build models of enterprise bankruptcy forecasting, but the accuracy of these models is usually quite low. The reason for that is the imbalanced nature of training data sets (the share of bankrupt firms is a small percent of the total number of firms). Nowadays, such machine learning methods as the random forest and the gradient boosting are becoming widespread. This study focuses on the use of extreme gradient boosting to predict bankruptcy. Extreme gradient boosting, using LASSO or Ridge regularization, penalizes complex models to avoid overfitting. Also, during training, extreme gradient boosting fills in the missing values of the data set, depending on the value of the loss. In this article, we proposed SMOTE technique to enhance the minority class of the training data sets, which helps to improve the performance of extreme gradient boosting. The experiment results of improved extreme gradient boosting are compared to the outcomes obtained by other methods.
References
Altman E.I. Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy. The Journal of Finance. 1968. Vol. 23, no. 4. P. 589–609. DOI: 10.1111/j.1540-6261.1968.tb00843.x.
Lugovskaya L. Predicting Default of Russian Smes on the Basis of Financial and Nonfinancial Variables. Journal of Financial Services Marketing. 2010. Vol. 14, no. 4. P. 301–313. DOI: 10.1057/fsm.2009.28.
Deakin E. A Discriminant Analysis of Predictors of Business Failure. Journal of Accounting Research. 1972. Vol. 10, no 1. P. 167–179. DOI: 10.2307/2490225.
Antunesa F., Ribeiroa B., Pereirab F. Probabilistic Modeling and Visualization for Bankruptcy Prediction. Applied Soft Computing. 2017. Vol. 60. P. 831–843. DOI: 10.1016/j.asoc.2017.06.043.
Ohlson J.A. Financial Ratios and the Probabilistic Prediction of Bankruptcy. Journal Of Accounting Research. 1980. Vol. 18, no. 1. P. 109–131. DOI: 10.2307/2490395.
Martin D. Early Warning of Bank Failure: a Logit Regression Approach. Journal of Banking & Finance. 1977. Vol. 1, no. 3. P. 249–276.
Wiginton J.C. A Note on the Comparison of Logit and Discriminant Models of Consumer Credit Behavior. Journal of Financial and Quantitative Analysis. 1980. Vol. 15. P. 757–770. DOI: 10.2307/2330408.
Begley J., Ming J., Watts S. Bankruptcy Classification Errors in the 1980s: an Empirical Analysis of Altman’s and Ohlson’s Models. Review of Accounting Studies. 1996. Vol. 1, no. 4. P. 267–284. DOI: 10.1007/bf00570833.
Wilson R.L, Sharda R. Bankruptcy Prediction Using Neural Networks. Decision Support Systems. 1994. Vol. 11, no. 5. P. 545–557. DOI: 10.1016/0167-9236(94)90024-8.
Tam K.Y., Kiang M.Y. Managerial Applications of Neural Networks: the Case of Bank Failure Predictions. Management science. 1992. Vol. 38, no. 7. P. 926–947. DOI: 10.1287/mnsc.38.7.926.
Altman E.I., Marco G., Varetto F. Corporate Distress Diagnosis: Comparisons Using Linear Discriminant Analysis and Neural Networks (the Italian Experience). Journal of Banking & Finance. 1994. Vol. 18, no. 3. P. 505–529. DOI: 10.1016/0378-4266(94)90007-8.
Ciampi F., Vallini C., Gordini N. Using Artificial Neural Networks Analysis for Small Enterprise Default Prediction Modeling: Statistical Evidence from Italian Firms. Oxford Business & Economics Conference Proceedings, Association for Business and Economics Research, ABER. 2009. Vol. 1. P. 126.
Wei L., Li J., Chen Z. Credit Risk Evaluation Using Support Vector Machine with Mixture of Kernel. Proceedings of the 7th International Conference on Computational Science. Lecture Notes in Computational Science and Engineering. 2007. Vol. 4488. P. 431–438. DOI: 10.1007/978-3-540-72586-2_62.
Härdle W.K., Lee Y.J., Schäfer D. The Default Risk of Firms Examined with Smooth Support Vector Machines. Discussion Papers, German Institute for Economic Research. 2007. Vol. 757. P. 1–30. DOI: 10.2139/ssrn.2894311.
Zieba M., Tomczak S.K., Tomczak J.M. Ensemble Boosted Trees with Synthetic Features Generation in Application to Bankruptcy Prediction. Expert Systems with Applications. 2016. Vol. 58. P. 93–101. DOI: 10.1016/j.eswa.2016.04.001.
Xia Y., Liu C.,. Li Y, Liu N. A Boosted Decision Tree Approach Using Bayesian Hyper-Parameter Optimization for Credit Scoring. Expert Systems With Applications. 2017. Vol. 78. P. 225–241. DOI: 10.1016/j.eswa.2017.02.017.
Zhou L. Performance of Corporate Bankruptcy Prediction Models on Imbalanced Dataset: The Effect of Sampling Methods. Knowledge-Based Systems. 2013. Vol. 41. P. 16–25. DOI: 10.1016/j.knosys.2012.12.007.
Kim T., Ahn H. A Hybrid Under-Sampling Approach for Better Bankruptcy Prediction. Journal of Intelligent Information Systems. 2015. Vol. 21, no 2. P. 173–190. DOI: 10.13088/jiis.2015.21.2.173.
Veganzonesa D., Séverina E. An Investigation of Bankruptcy Prediction in Imbalanced Datasets. Decision Support Systems. 2018. no. 112. P. 111–124. DOI: 10.1016/j.dss.2018.06.011.
Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM. 2016. P. 785–794. DOI: 10.1145/2939672.2939785.
Friedman J.H. Stochastic Gradient Boosting. Computational Statistics and Data Analysis. 2002. no. 38. P. 367–378. DOI: 10.1016/j.eswa.2016.04.001.
