Corporate financial distress prediction in a transition economy

Journal of Forecasting - Tập 43 Số 8 - Trang 3128-3160 - 2024
Minh Nguyen1, Bang Nguyen2, Minh‐Lý Liêu3
1Department of Accounting and Information Systems, Broad College of Business Michigan State University East Lansing Michigan USA
2Faculty of Data Science University of Finance ‐ Marketing Ho Chi Minh City Vietnam
3IÉSEG School of Management University of Lille, CNRS, UMR 9221 ‐ LEM ‐ Lille Economie Management Lille France

Tóm tắt

Abstract

Forecasting financial distress of corporations is a difficult task in economies undergoing transition, as data are scarce and are highly imbalanced. This research tackles these difficulties by gathering reliable financial distress data in the context of a transition economy and employing the synthetic minority oversampling technique (SMOTE). The study employs seven different models, including linear discriminant analysis (LDA), logistic regression (LR), support vector machines (SVMs), neural networks (NNs), decision trees (DTs), random forests (RFs), and the Merton model, to predict financial distress among publicly traded companies in Vietnam between 2011 and 2021. The first six models use accounting‐based variables, while the Merton model utilizes market‐based variables. The findings indicate that while all models perform fairly well in predicting results for nondelisted firms, they perform somewhat poorly in predicting results for delisted firms in terms of various measures including balanced accuracy, Matthews correlation coefficient (MCC), precision, recall, and score. The study shows that the models that incorporate both Altman's and Ohlson's variables consistently outperform those that only use Altman's or Ohlson's variables in terms of balanced accuracy. Additionally, the study finds that NNs are generally the most effective models in terms of both balanced accuracy and MCC. The most important variable in Altman's variables as well as the combination of Altman's and Ohlson's variables is “reat” (retained earnings on total assets), whereas “ltat” (total liabilities on total assets) and “wcapat” (working capital on total assets) are the most important variables in Ohlson's variables. The study also reveals that in most cases, the models perform better in predicting results for big firms than for small firms and typically better than in good years than for bad years.

Từ khóa


Tài liệu tham khảo

10.1016/j.jbankfin.2020.105959

10.1016/j.jempfin.2015.09.004

10.1111/j.1540-6261.1968.tb00843.x

10.1002/9781119541929

10.1111/jifm.12053

10.3390/jrfm12020055

10.2307/2490171

10.1016/j.mcm.2006.12.012

10.1093/rfs/hhn044

10.1086/260062

Boser B. E. Guyon I. M. &Vapnik V. N.(1992).A training algorithm for optimal margin classifiers. InProceedings of the Fifth Annual Workshop on Computational Learning Theory pp.144–152.

10.1016/j.jcorpfin.2019.101541

10.1613/jair.953

10.1142/S0219091506000744

10.1016/j.eswa.2008.03.020

10.1007/s40815-015-0121-5

10.2307/3665168

10.1007/BF00994018

10.2307/2325486

10.1111/j.1469-1809.1936.tb02137.x

10.1016/j.ejor.2014.08.016

10.1002/for.1153

10.1007/BF02295137

10.1504/IJBG.2014.063392

10.1023/B:RAST.0000013627.90884.b7

Hoang T. H. V., 2020, Applying Z‐score model in predicting bankruptcy of enterprises in Vietnam (in vietnamese), Banking Science & Training Review, 217, 43

10.1016/j.eswa.2018.09.039

Hsu C.‐W. Chang C.‐C. &Lin C.‐J.(2016).A practical guide to support vector classification. Available athttps://www.csie.ntu.edu.tw/∼cjlin/papers/guide/guide.pdf. Accessed on 03/17/2023.

10.2469/faj.v59.n1.2501

Lam C. D., 2009, Application of KMV‐Merton model to the quantification of relations between the assets guarantee, the borrower's funds appointment and the credit risk (in Vietnamese), Journal of Science and Technology, 2, 1

Le D. C., 2012, Using CVaR and KMV‐Merton model to estimate the default probability: Empirical evidence from Vietnam (in Vietnamese), Journal of Development and Integration, 5, 10

10.1016/j.eswa.2011.02.084

10.1016/j.knosys.2008.03.047

Lieu M. L., 2014, Estimation of default probability by using Z‐score and H‐score models for listed companies in Vietnam (in Vietnamese), Banking Technology Review, 105, 21

10.1080/00036840802167350

10.1016/j.ejor.2018.10.024

10.1111/j.1540-6261.1974.tb03058.x

Nguyen D. T., 2017, Measuring credit risk of listed firms in Vietnam (in Vietnamese), Review of Finance, 654, 52

Nguyen T. C., 2014, Using KMV‐Merton to estimate credit risk of corporate customers and potential loss for banks (in Vietnamese), Journal of Economic Development, 289, 39

Nguyen V. H., 2015, Using Z‐score model to test internal credit risk ranking and estimate probability of default (in Vietnamese), Journal of Finance and Accounting Research, 8, 26

10.1016/j.ecosys.2018.05.002

Odom M. D. &Sharda R.(1990).A neural network model for bankruptcy prediction. InThe 1990 IJCNN International Joint Conference on Neural Networks pp.163–168.

10.2307/2490395

10.1111/j.1540-6261.1994.tb00086.x

10.1016/j.cor.2004.06.023

10.1111/j.2517-6161.1948.tb00008.x

10.1016/j.jfs.2007.02.001

10.5539/gjhs.v8n7p41

10.1016/j.eswa.2004.08.009

10.1086/209665

10.1007/s10614-022-10244-8

10.1016/j.eswa.2011.01.042

10.1016/j.knosys.2006.11.003

Tanthanongsakkun S., 2011, A comparison of corporate bankruptcy models in australia: The Merton vs accounting‐based models, Asia‐Pacific Journal of Risk and Insurance, 3, 1

10.1016/j.eswa.2009.07.081

10.1142/S0219024905003256

10.1111/j.1540-6261.2004.00650.x

10.5539/ijef.v6n6p1

10.3390/jrfm12040155

Vo X. V., 2015, Using accounting ratios in predicting financial distress: An empirical investigation in the vietnam stock market, Journal of Economics and Development, 17, 41

10.13106/jafeb.2019.vol6.no4.53

10.1108/17506140710758008

10.1016/0167-9236(94)90024-8

10.1007/s11135-010-9376-y

10.1016/j.knosys.2012.04.004

Zheng Q. &Yanhui J.(2007).Financial distress prediction based on decision tree models. In2007 IEEE International Conference on Service Operations and Logistics and Informatics pp.1–6.

10.2307/2490859