Classification of Company Performance Status Using Ensemble Learning and SMOTE by Considering CGI
The global financial crisis that occurred in 2008 made most companies disturbed and unstable. In Indonesia, the impact of the global financial crisis can be felt continuously at the end of 2008. Indonesia's economic growth began from 2008-2009, the lowest percentage in 2009. This shows that the Indonesian economy is very important by the global financial crisis in 2009. Important for company to measure and know the status of the company's financial condition. A predictive model is needed to assist in analyzing the company's performance status for risk management. Therefore, building an effective Financial Distress Prediction (FDP) model has become an important research topic. This study aims to develop the FDP model by combining the ensemble learning method with the Synthetic Minority Oversampling Technique (SMOTE) method in state-owned companies in Indonesia listed on the Indonesia Stock Exchange. Then, in addition to using Financial Ratios (FR), this study also considers Corporate Governance Indicators (CGI). The experimental results of the FDP model development fell on the SMOTE-Stacking with an Accuracy result of 0.99 using FRs and CGIs data. This proves that the use of SMOTE and CGI methods is able to provide maximum prediction results. The result of this study is the FDP model which includes the company's performance status which is expected to increase the accuracy of the FDP model's performance.
 Veganzones, D. and Séverin, E. (2018) ‘An investigation of bankruptcy prediction in imbalanced datasets’, Decision Support Systems, 112, pp. 111–124. doi: 10.1016/j.dss.2018.06.011.
 Tsai, C. F. and Wu, J. W. (2008) ‘Using neural network ensembles for bankruptcy prediction and credit scoring’, Expert Systems with Applications, 34(4), pp. 2639–2649. doi: 10.1016/j.eswa.2007.05.019.
 Tsai, C. F., Hsu, Y. F. and Yen, D. C. (2014) ‘A comparative study of classifier ensembles for bankruptcy prediction’, Applied Soft Computing Journal, 24, pp. 977–984. doi: 10.1016/j.asoc.2014.08.047.
 Ding, Y., Song, X. and Zen, Y. (2008) ‘Forecasting financial condition of Chinese listed companies based on support vector machine’, Expert Systems with Applications, 34(4), pp. 3081–3089. doi: 10.1016/j.eswa.2007.06.037.
 Zhang, L., Altman, E. I. and Yen, J. (2010) ‘Corporate financial distress diagnosis model and application in credit rating for listing firms in China’, Frontiers of Computer Science in China, 4(2), pp. 220–236. doi: 10.1007/s11704-010-0505-5.
 Huang, C., Dai, C. and Guo, M. (2015) ‘A hybrid approach using two-level DEA for financial failure prediction and integrated SE-DEA and GCA for indicators selection’, Applied Mathematics and Computation, 251, pp. 431–441. doi: 10.1016/j.amc.2014.11.077.
 Liang, D. et al. (2020) ‘Combining corporate governance indicators with stacking ensembles for financial distress prediction’, Journal of Business Research, 120(December 2019), pp. 137–146. doi: 10.1016/j.jbusres.2020.07.052.
 Kim, K. J., Lee, K. and Ahn, H. (2019) ‘Predicting corporate financial sustainability using Novel Business Analytics’, Sustainability (Switzerland), 11(1), pp. 1–17. doi: 10.3390/su11010064.
 Zhou, L., Tam, K. P. and Fujita, H. (2016) ‘Predicting the listing status of Chinese listed companies with multi-class classification models’, Information Sciences, 328, pp. 222–236. doi: 10.1016/j.ins.2015.08.036.
 Sun, J. et al. (2021) ‘Multi-class financial distress prediction based on support vector machines integrated with the decomposition and fusion methods’, Information Sciences, 559, pp. 153–170. doi: 10.1016/j.ins.2021.01.059.
 Chen, T. and Guestrin, C. (2016) ‘XGBoost: A Scalable Tree Boosting System’, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 19(6).
 Ziȩba, M., Tomczak, S. K. and Tomczak, J. M. (2016) ‘Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction’, Expert Systems with Applications, 58, pp. 93–101. doi: 10.1016/j.eswa.2016.04.001.
 Graczyk, M. et al. (2010) ‘Comparison of bagging, boosting and stacking ensembles applied to real estate appraisal’, International Conference on Intelligent Information and Database Systems: Part II, pp. 340–350.
 Pisula, T. (2020) ‘An Ensemble Classifier-Based Scoring Model for Predicting Bankruptcy of Polish Companies in the Podkarpackie Voivodeship’, Journal of Risk and Financial Management, 13(2), p. 37. doi: 10.3390/jrfm13020037.
 Sun, J., Shang, Z. and Li, H. (2014) ‘Imbalance-oriented SVM methods for financial distress prediction: A comparative study among the new SB-SVM-ensemble method and traditional methods’, Journal of the Operational Research Society, 65(12), pp. 1905–1919. doi: 10.1057/jors.2013.117.
 Brown, I. and Mues, C. (2012) ‘An experimental comparison of classification algorithms for imbalanced credit scoring data sets’, Expert Systems with Applications, 39(3), pp. 3446–3453. doi: 10.1016/j.eswa.2011.09.033.
 Daily, C. M. and Dalton, D. a N. R. (1994) ‘Research notes and communications corporate governance and the bankrupt firm: an empirical assessment’, Strategic Management Journal, 15(December 1992), pp. 643–654.
 Chen, I. J. (2014) ‘Financial crisis and the dynamics of corporate governance: Evidence from Taiwan’s listed firms’, International Review of Economics and Finance, 32, pp. 3–28. doi: 10.1016/j.iref.2014.01.004.
 Brédart, X. (2014) ‘Financial Distress and Corporate Governance: The Impact of Board Configuration’, International Business Research, 7(3), pp. 72–80. doi: 10.5539/ibr.v7n3p72.
Geng, R., Bose, I. and Chen, X. (2015) Prediction of financial distress: An empirical study of listed Chinese companies using data mining, European Journal of Operational Research.
 Liang, D. et al. (2016) ‘Financial ratios and corporate governance indicators in bankruptcy prediction: A comprehensive study’, European Journal of Operational Research, 252(2), pp. 561–572. doi: 10.1016/j.ejor.2016.01.012.
 Sun, J. et al. (2020) ‘Class-imbalanced dynamic financial distress prediction based on Adaboost-SVM ensemble combined with SMOTE and time weighting’, Information Fusion, 54(July 2019), pp. 128–144. doi: 10.1016/j.inffus.2019.07.006.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
JATIS oleh http://jurnal.mdp.ac.id/index.php/jatisi disebarluaskan di bawah Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional.