VSTE
Littera Scripta

ISSN (online): 1805-9112

Research ArticleOpen access

Mitigating challenges: Handling mis sing values and imbalanced data in bankruptcy prediction using machine learning

Ednawati Rainarli1iD, Amine Sabek2iD

  1. Universitas Komputer Indonesia
  2. University of Tamanghasset

Abstract

The research on financial distress has become essential because the predicted results can serve as an early warning for managers, investors, and banks. Financial ratios calculated in financial reports can serve as indicators to assess the company's condition. One of the approaches used for bankruptcy prediction is employing machine learning methods. Data requirements with balanced classes and the need to process data with complete parameters/features are prerequisites for building an accurate bankruptcy prediction model. In this study, we employed data balancing techniques such as downsampling and filling missing feature values using the average of nearest neighbors in data preprocessing before training the prediction model. From our experiments, we found that by addressing missing values and balancing the data, the F1 score of the prediction model using Random Forest (RF) improved by 30% compared to not addressing missing data and data imbalance. Although our testing used the Polish company dataset, which may have different characteristics from companies in other countries, the proposed strategies can serve as an initial approach for training datasets of other companies using machine learning methods.

Keywords:Bankruptcy predictionfinancial distressimbalanced datamachine learningmissing value

References

  1. ALTMAN E.I (1968). Financial Ratios, Discriminant Analysis And The Prediction Of Corpporate Bankruptcy, The Journal Of Finance, XXIII(4), pp. 589–609.
  2. ATIYA A.F (2001). Bankruptcy prediction for credit risk using neural networks: A survey and new results, IEEE Transactions on Neural Networks, 12(4), pp. 929–935. Available at: https://doi.org/10.1109/72.935101.
  3. Barboza, F., Kimura, H., Altman, E (2017). Machine learning models and bankruptcy prediction, Expert Systems with Applications, 83, pp. 405–417. Available at: https://doi.org/ 10.1016/j.eswa.2017.04.006.
  4. Bateni, L., Asghari, F (2020). Bankruptcy prediction using logit and genetic algorithm models: A comparative analysis, Computational Economics, 55(1), pp. 335–348. Available at: https://doi.org/10.1007/s10614-016-9590-3.
  5. BRÎNDESCU-OLARIU D., GOLEŢ I., 2013. Bankruptcy prediction ahead of global recession: Discriminant analysis applied on Romanian companies in Timis Country, Timisoara Journal of Economics and Business, 6(19), pp. 70–94. Available at: https://doi.org/10.1515/ 9783112597569-toc.
  6. Cleofas-Sánchez, L., García, V., Marqués, A.I., SÁNCHEZ J.S (2016). Financial distress prediction using the hybrid associative memory with translation, Applied Soft Computing Journal, 44, pp. 144–152. Available at: https://doi.org/10.1016/ j.asoc.2016.04.005.
  7. Cultrera, L., Croquet, M., Jospin, J (2017). Predicting bankruptcy of Belgian SMEs: A Hybrid approach based on factorial analysis, International Business Research, 10(3), p. 33. Available at: https://doi.org/10.5539/ibr.v10n3p33.
  8. Dalianis, H (2018). Evaluation Metrics and Evaluation, in Clinical Text Mining. Springer, Cham., pp. 45–53. Available at: https://doi.org/10.1007/978-3-319-78503-5_6.
  9. Danenas, P., Garsva, G (2015). Selection of Support Vector Machines based classifiers for credit risk domain, Expert Systems with Applications, 42(6), pp. 3194–3204. Available at: https://doi.org/10.1016/j.eswa.2014.12.001.
  10. Dzik-Walczak, A., Odziemczyk, M (2021). Modelling cross-sectional tabular data using convolutional neural networks: Prediction of corporate bankruptcy in Poland, Central European Economic Journal, 8(55), pp. 352–377. Available at: https://doi.org/ 10.2478/ceej-2021-0024.
  11. KHAN U.E (2018). Bankruptcy prediction for financial sector of Pakistan: Evaluation of logit and discriminant analysis approaches, Pakistan Journal of Engineering, Technology & Science, 6(2), pp. 210–220. Available at: https://doi.org/10.22555/pjets.v6i2.1966.
  12. Korol, T (2012). Fuzzy logic in financial management, in Fuzzy Logic - Emerging Technologies and Applications. InTech, pp. 259–286. Available at: https://doi.org/10.5772/35574.
  13. Kotsiantis, S., Kanellopoulos, D., Pintelas, P (2006). Handling imbalanced datasets: A review, GESTS International Transactions on Computer Science and Engineering, 30(1), pp. 25–36. Available at: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.96.9248 &rep=rep1&type=pdf.
  14. Lee, S., CHOI W.S (2013). A multi-industry bankruptcy prediction model using back-propagation neural network and multivariate discriminant analysis, Expert Systems with Applications, 40(8), pp. 2941–2946. Available at: https://doi.org/10.1016/j.eswa.2012. 12.009.
  15. Mihalovič, M (2016). Performance comparison of multiple discriminant analysis and logit models in bankruptcy prediction, Economics and Sociology, 9(4), pp. 101–118. Available at: https://doi.org/10.14254/2071-789X.2016/9-4/6.
  16. Pavlicko, M., Mazanec, J (2022). Minimalistic logit model as an effective tool for predicting the risk of financial distress in the Visegrad group, Mathematics, 10(8), pp. 1–22. Available at: https://doi.org/10.3390/math10081302.
  17. Quynh, T.D., THI LAN PHONG T (2020). Improving the bankruptcy prediction by combining some classification models, in 2020 12th International Conference on Knowledge and Systems Engineering. IEEE, pp. 263–268. Available at: https://doi.org/10.1109/KSE50997.2020. 9287707.
  18. Rainarli, E (2019). The Comparison of machine learning model to predict bankruptcy: Indonesian stock exchange data, in IOP Conference Series: Materials Science and Engineering. Bandung: IOP, pp. 6–12. Available at: https://doi.org/10.1088/1757-899X/662/5/052019.
  19. Rainarli, E., Aaron, A (2015). The implementation of fuzzy logic to predict the bankruptcy of company in Indonesia, International Journal of Business and Administrative Studies, 1(4), pp. 147– 154. Available at: https://doi.org/10.20469/ ijbas.10003-4.
  20. Sabek, A (2023). Unveiling the diverse efficacy of artificial neural networks and logistic regression: A comparative analysis in predicting financial distress. Croatian Review of Economic, Business and Social Statistics, CREBSS), 9(1), 16-32. Available at: http://doi.org/ 10.2478/crebss-2023-0002.
  21. Sabek, A.,, Horak, J (2023). Gaussian process regression´s hyperparameters optimization to predict financial distress. Retos, Revista de Ciencias Administrativas y EconA3micas, 13(26), 273- 289. Available at: https://doi.org/10.17163/ret.n26. 2023.06.
  22. Sun, J., Hui, L., Qing-Hua, H., Kai-Yu, H (2014). Predicting financial distress and corporate failure: A review from the state-of-the-art definitions, modeling, sampling, and featuring approaches, Knowledge-Based Systems, 57, pp. 41–56. Available at: https://doi.org/ 10.1016/ j.knosys.2013.12.006.
  23. TOMCZAK S., 2016 Polish companies bankruptcy data, Machine Learning Repository. Available at: https://doi.org/ttps://doi.org/10.24432/C5F600.
  24. Tsai, C.F., Hsu, Y.F., YEN D.C (2014). A comparative study of classifier ensembles for bankruptcy prediction, Applied Soft Computing Journal, 24, pp. 977–984. Available at: https://doi.org/10.1016/j.asoc.2014.08.047.
  25. Zahin, S.A., Ahmed, C.F., Alam, T (2018). An effective method for classification with missing values, Applied Intelligence, 48(10), pp. 3209–3230. Available at: https://doi.org/10.1007/ s10489-018- 1139-9.