Plekhanov Russian University of Economics, Moscow, Russia:

N. A. Kazakova, Dr. Econ., Professor of the Basic Dept. of Financial and Economic Security, e-mail: axd_audit@mail.ru
E. A. Sergeeva, Business Analyst, Accountant

The digital economy has changed the priorities for assessing business performance: there have been significant changes in the structure of assets of organizations, criteria for stability, liquidity, growth and business risks. In this regard, bankruptcy analysis methods should be adapted to the use of information resources, big data technologies, and current legal regulation in the relevant areas. Many researchers and practitioners consider logistic regression analysis to be a more reliable method for assessing the likelihood of bankruptcy in the short and medium term, the models of which provide more accurate value. The aim of the study is to substantiate a risk-factor approach to building a regression logit model to predict the likelihood of bankruptcy of ferrous metallurgy companies, which makes it possible to increase the reliability of diagnosing key risks that contribute to the growth of business financial insolvency. In comparison with the published examples of constructing logit models, the authors used a new approach focused on the grouping of risks that are normatively defined by international standards, corresponding to the most significant factors identified as a result of industry analysis. The classification of risks is the basis for the selection of model`s factor indicators, which was carried out by the method of correlation analysis and assessment of their statistical significance on the data of ferrous metallurgy companies. To build the model, the data for 2016–2020 were calculated and used, downloaded from the information system for professional analysis of markets and companies and the Unified State Register of Legal Entities for 29 companies in the metallurgical industry, the main activity of which is included in OKVED 24.1 “Production of iron, steel and ferroalloys”, including those declared bankrupt as of June 2021. The model was tested on 8 companies that were not included in the sample. To assess the quality of the resulting logistic regression model, a receiver operating characteristic curve (ROC-curve) was constructed, the statistical indicator AUC was calculated, and the limiting effects of factor indicators were determined. The resulting model showed a fairly high level of forecast reliability (over 85%).

The article is prepared within the framework of the scientific and research work of Plekhanov Russian University of Economics according to the theme "Monitoring of sectoral risks of financial safety in the digital medium using the Harvard paradigm of industrial branch analysis".

1. The structure of Russia’s GDP. Official website of the Federal State Statistics Service. Available at: https://rosstat.gov.ru/ (accessed: 16.07.2021).
2. Kazakova N. А., Kogdenko V. G., Kuzmina-Merlino I., Sivkova А. Е. Assessment and forecasting of economic sustainability of Russian metallurgical companies. Chernye Metally. 2020. No. 4. pp. 60–67.
3. Spark-Interfax Information system. Available at: http://www.spark-interfax.ru (accessed: 16.07.2021).
4. Kerkhoff H. J. Iron and steel industry: rising uncertainty. Chernye Metally. 2018. No. 5. pp. 61–65.
5. Kijewska A. Conditions for sustainable growth (SGR) for companies from metallurgy and mining sector in Poland. Metalurgija. 2016. Vol. 55. No. 1. pp. 139–142.
6. Official website of PJSC Severstal. Available at: https://www.severstal.com/rus/ir/disclosure/financial_reports/ (accessed: 16.07.2021).
7. Dluhošová D., Ptáčková B., Richtarová D. Financial performance evaluation of metallurgy of the Czech Republic. METAL 2018 – 27^th International Conference on Metallurgy and Materials. 2018. pp. 2055–2061.
8. Kazakova N., Gendon A., Sedova N., Khlevnaya E. Estimation of factors and projected growth of the metallurgical branch of Russia under unstable market conditions. Metalurgija. 2018. Vol. 57. No. 4. pp. 360–362.
9. Adno Yu. L. World ferrous metallurgy: crisis around the turn of a new decade. Chernye Metally. 2020. No. 7. pp. 51–58.
10. Russian industry of the covid period. Available at: https://www.metalinfo.ru/emagazine/2021/0708/48/ (accessed: 16.07.2021).
11. Statistical release of the Federal resource “Bankruptcy in Russia: results of 2020”. Available at: https://fedresurs.ru/news/e3fc79ce-fd38-432f-ab08-8c1561b1b7cb (accessed: 16.07.2021).
12. Analytical Bulletin Metallurgy: Trends and Forecasts. Results of 2019. Available at: http://vid1.rian.ru/ig/ratings/metallurgy_demo37.pdf (accessed: 16.07.2021).
13. How the metallurgy industry can more easily survive the consequences of the pandemic. Available at: https://www2.deloitte.com/ru/ru/pages/about-deloitte/deloitte-in-press/2020/kak-metallurgicheskoj-otrasli-legche-perezhit-posledstviya-pandemii.html (accessed: 16.07.2021).
14. Analytical Bulletin Metallurgy: Trends and Forecasts. Results of 2020. Available at: http://vid1.rian.ru/ig/ratings/metallurgy_demo.pdf (accessed: 16.07.2021).
15. Express analysis of the ferrous metallurgy market in the new economic conditions: enterprises are preparing for a protracted crisis. Available at: https://metallurgprom.org/articles/analytics/3823-jekspress-analiz-rynka-chernoj-metallurgii-v-novyh-jekonomicheskihuslovijah-predprijatija-gotovjatsja-k-zatjazhnomu-krizisu.html (accessed: 16.07.2021).
16. Damodaran А. Strategic risk management: principles and methodology. Available at: http://pages.stern.nyu.edu/~adamodar/ (accessed: 16.07.2021).
17. Zinovyeva E. G., Koptyakova S. V. Assessment of intgration risks for metallurgical enterprises using the fuzzy set method. CIS Iron and Steel Review. 2019. Vol. 17. pp. 58–64. DOI: 10.17580/cisisr.2019.01.11.
18. Rabdanova V. V. Review of logit-regression models for predicting bankruptcy of enterprises. Vestnik BSGTU. 2016. No. 4. pp. 129–134.
19. Kazakov А. V., Kolyshkin А. V. Development of bankruptcy forecasting models in modern Russian conditions. Vestnik Sankt-Peterburgskogo universiteta. Ekonomika. 2018. No. 2. pp. 241–266.
20. Unified State Register of Legal Entities. Available at: https://egrul.nalog.ru (accessed: 16.07.2021).
21. Information of the Ministry of Finance of Russia No. ПЗ-9/2012 “On Disclosure of Information on the Risks of an organization’s economic activity in the annual financial statements”. Available at: http://www.consultant.ru/document/cons_doc_LAW_135436/ (accessed: 16.07.2021).
22. Logistic regression and ROC analysis - mathematical apparatus. Loginom Company. Available at: https://loginom.ru/blog/logistic-regression-roc-auc (accessed: 16.07.2021).
23. Dyakonov А. G. AUC ROC (area under the error curve). Small data analysis. 2017. Available at: https://dyakonov.org/2017/07/28/auc-roc-площадь-под-кривой-ошибок/ (accessed: 16.07.2021).