Bankruptcy Risk Factors of Russian Companies

The bankruptcy of Russian companies in the existing environment has become rather common. Determination of bankruptcy risk factors allows predicting the prospects for business development. The authors set the task to determine the relative influence

of individual financial and non-financial factors on the probability of a company’s bankruptcy. To study risk factors, the authors analyzed 3184 large Russian companies (with revenues of more than 2 billion rubles per year and more than 250 employees) of various industries operating from 2009 to 2020. The total number of observations is 38,208. For analysis, 30 factors were selected and divided into five groups: profitability, liquidity, turnover, financial stability and general (non-financial) factors. For the study, one of the machine learning methods was used – the random forest method. The sample consists of companies from seven industries, including manufacturing, retail, construction, electric power, mining, agricultural production, and water supply, as well as other industries, which include companies in education, healthcare, agriculture, and hospitality. The analysis was carried out both in aggregate for the entire sample without being distributed by industry, and for samples distributed by manufacturing, retail, and service industries. In the sample as a whole, the tested model in 86% of cases correctly predicted the possibility of a company going bankrupt for the period under review. This result confirmed that machine learning methods (in particular, the random forest algorithm) are highly effective in solving the problem of bankruptcy prediction for a company. Based on the data obtained, the paper concludes that profitability factors have the most significant impact on the probability of bankruptcy for manufacturing and retail companies. For service companies, it is financial stability factors. Solving the problem of determining the bankruptcy risk factors of Russian companies will ensure a reduction in the number of bankrupt enterprises, which, in turn, will contribute to the recovery and development of the national economy.

1. Altman E. I. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance. 1968;23(4):589–609. DOI: 10.1111/J.1540–6261.1968.TB00843.X

2. Altman E. I., Fargher N., Kalotay E. A simple empirical model of equity-implied probabilities of default. The Journal of Fixed Income. 2011;20(3):71–85. DOI: 10.3905/jfi.2011.20.3.071

3. Altman E. I., Iwanicz-Drozdowska M., Laitinen E., Suvas A. Distressed firm and bankruptcy prediction in an international context: A review and empirical analysis of Altman’s Z-score model. SSRN Electronic Journal. 2014. DOI: 10.2139/ssrn.2536340

4. Agarwal V., Taffler R. J. Twenty-five years of the Taffler Z-score model: Does it really have predictive ability? Accounting and Business Research. 2007;37(4):285–300. DOI: 10.1080/00014788.2007.9663313

5. Zmijewski M. Methodological issues related to the estimation of financial distress prediction models. Journal of Accounting Research. 1984;22:59–82. DOI: 10.2307/2490859

6. Ohlson J. Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research. 1980;18(1):109–131. DOI: 10.2307/2490395

7. Karminsky A. M., Burekhin R. N. Comparative analysis of methods for forecasting bankruptcies of Russian construction companies. Business Informatics. 2019;13(3):52–66. DOI: 10.17323/1998–0663.2019.3.52.66 (In Russ.: Biznes-informatika. 2019;13(3):52–66. DOI: 10.17323/1998–0663.2019.3.52.66).

8. Jones S., Hensher D. A. Predicting firm financial distress: A mixed logit model. The Accounting Review. 2004;79(4):1011–1038. DOI: 10.2308/accr.2004.79.4.1011

9. Haydarshina G. A. Improvement of methods for assessing risk of bankruptcy of Russian enterprises in modern conditions. Imushchestvennye otnosheniya v Rossiiskoi Federatsii = Property Relations in the Russian Federation. 2009;(8):86–95. (In Russ.).

10. Karminsky A. M., Kostrov A. V., Murzenkov T. N. Modeling of the probability of default of Russian banks using econometric methods. Preprint WP7/2012/04. Moscow: NRU HSE; 2012. 64 p. (In Russ.).

11. Behr A., Weinblat J. Default patterns in seven EU countries: A random forest approach. International Journal of the Economics of Business. 2017;24(2):181–222. DOI: 10.1080/13571516.2016.1252532

12. Li Y., Wang Y. Machine learning methods of bankruptcy prediction using accounting ratios. Open Journal of Business and Management. 2018;6(1):1–20. DOI: 10.4236/ojbm.2018.61001

13. Joshi S., Ramesh R., Tahsildar S. A bankruptcy prediction model using random forest. In: 2nd Int. conf. on intelligent computing and control systems (ICICCS). (Madurai, 14–15 June 2018). Piscataway, NJ: IEEE; 2018. DOI: 10.1109/ICCONS.2018.8663128

14. Denisov D. V., Smirnova D. K. Application of random forest method to estimate the incurred but not reported claims reserve of an insurance company. International Journal of Open Information Technologies. 2016;4(7):45–50. (In Russ.).

15. Gruzdev A. V. Random forest method in scoring. Risk-menedzhment v kreditnoi organizatsii. 2014;(1):28–43. (In Russ.).

16. Kazakov A. V., Kolyshkin A. V. The development of bankruptcy prediction models in modern Russian economy. Vestnik Sankt-Peterburgskogo universiteta. Ekonomika = St. Petersburg University Journal of Economic Studies (SUJES). 2018;34(2):241–266. (In Russ.). DOI: 10.21638/11701/spbu05.2018.203

17. Kolyshkin A. V., Gilenko E. V., Dovzhenko S. E., Zhilkin S. A., Choe S. E. Forecasting the financial insolvency of enterprises. Vestnik Sankt-Peterburgskogo universiteta. Ekonomika = St. Petersburg University Journal of Economic Studies (SUJES). 2014;(2):122–142. (In Russ.).

18. Fedorova E. A., Gilenko E. V., Dovzhenko S. E. Models for bankruptcy forecasting: Case study of Russian enterprises. Studies on Russian Economic Development. 2013;24(2):159–164. (Russ. ed.: Problemy prognozirovaniya. 2013;(2):85–92.).

19. Fedorova E. A., Musienko S. O., Fedorov F. Yu. Prediction of bankruptcy of small and medium-sized business entities in Russia. Finansy i kredit = Finance and Credit. 2018;24(11):2537–2552. (In Russ.). DOI: 10.24891/fc.24.11.2537

20. Demeshev B., Tikhonova A. Default prediction for Russian companies: Intersectoral comparison. Ekonomicheskii zhurnal Vysshei shkoly ekonomiki = The HSE Economic Journal. 2014;18(3):359–386. (In Russ.).

21. Gorbatkov S., Beloliptsev I. A hybrid method for estimating the risk of bankruptcies based on Bayesian neural network ensemble and the logit-model. Naukovedenie. 2013;(6). URL: http://naukovedenie.ru/PDF/25EVN 613. pdf (In Russ.).

22. Makeeva E. Yu., Arshavsky I. V. Integration of neural networks and semantic interpretation for bankruptcy prediction. Korporativnye finansy = Journal of Corporate Finance Research. 2014;8(4):130–141. (In Russ.). DOI: 10.17323/j.jcfr.2073–0438.8.4.2014.130–141

23. Bogdanova T., Shevgunov T., Uvarova O. Using neural networks for solvency prediction for Russian companies of manufacturing industries. Business Informatics. 2013;(2):40–48. (In Russ.: Biznes-informatika. 2013;(2):40–48.).

24. Arinichev I. V., Bogdashev I. V. Estimation of bankruptcy risk of small business companies using methods of machine learning. Vestnik Rossiiskogo universiteta druzhby narodov. Seriya: Ekonomika = RUDN Journal of Economics. 2017;25(2):242–254. (In Russ.). DOI: 10.22363/2313–2329–2017–25–2–242–254

25. Liaw A., Wiener M. Classification and regression by randomForest. R News. 2002;2(3):18–22. URL: https://cogns.northwestern.edu/cbmg/LiawAndWiener2002.pdf

26. Gepp A., Kumar K. Predicting financial distress: A comparison of survival analysis and decision tree techniques. Procedia Computer Science. 2015;54:396–404. DOI: 10.1016/j.procs.2015.06.046

27. Altman E. I., Sabato G. Modelling credit risk from SMEs: Evidence from the US market. ABACUS: A Journal of Accounting, Finance and Business Studies. 2007;43(3):332–357. DOI: 10.1111/j.1467–6281.2007.00234.x

28. Zhdanov V. Yu., Afanaseva O. A. Bankruptcy risk diagnostics model for aviation enterprises. Korporativnye finansy = Journal of Corporate Finance Research. 2011;5(4):77–89. (In Russ.). DOI: 10.17323/j.jcfr.2073–0438.5.4.2011.77–89

29. Drezner Z., Marcoulides G., Stohs M. H. Financial applications of a Tabu search variable selection model. Journal of Applied Mathematics and Decision Sciences. 2001;5(4):215–234. DOI: 10.1155/S1173912601000165

30. Altman E. I., Sabato G., Wilson N. The value of non-financial information in SME risk management. Journal of Credit Risk. 2010;6(2):95–127. DOI: 10.21314/JCR.2010.110

31. Pererva O. L., Stepanov S. E., Nezimova S. S. Comparison of econometric models and methods of business analytics for prediction of bankruptcy of enterprises. Naukovedenie. 2017;9(6):1–9. URL: https://naukovedenie.ru/PDF/82EVN617.pdf (In Russ.).

32. Molina C. A. Are firms underleveraged? An examination of the effect of leverage on default probabilities. The Journal of Finance. 2005;60(3):1427–1459. DOI: 10.1111/j.1540–6261.2005.00766.x