ecr-journalЭкономическая наука современной РоссииEconomics of Contemporary Russia1609-14422618-8996Regional Public Organization for Assistance to the Development of Institutions of the Department of Economics of the Russian Academy of Sciences10.33293/1609-1442-2024-2(105)-101-124CXQVQDecr-journal-978Research ArticleЭКОНОМИЧЕСКАЯ ПОЛИТИКА И ХОЗЯЙСТВЕННАЯ ПРАКТИКАECONOMICAL POLICY AND ECONOMICAL PRACTICEМоделирование риска дефолта российских банков, 2015–2020 гг.Modeling the risk of bank defaulthttps://orcid.org/0000-0001-9107-3173ЩепелеваМария АлександровнаShchepelevaMarija A.

кандидат экономических наук, доцент

mshchepeleva@hse.ruТусипкалиевКайратTusipkalievKajratktusipkaliev@edu.hse.ruСтолбовМихаил ИосифовичStolbovMihail I.

доктор экономических наук, профессор

stolbov_mi@mail.ruНациональный исследовательский университет «Высшая школа экономики», МоскваРоссияNational Research University “Higher School of Economics” (HSE University), MoscowRussian FederationМосковский государственный институт международных отношений (МГИМО МИД России), МоскваРоссияMoscow State Institute of International Relations, MoscowRussian Federation20242807202402101124Copyright © Щепелева М.А., Тусипкалиев К., Столбов М.И., 20242024Щепелева М.А., Тусипкалиев К., Столбов М.И.Shchepeleva M.A., Tusipkaliev K., Stolbov M.I.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.ecr-journal.ru/jour/article/view/978

Исследование посвящено моделированию вероятности дефолта российских банков на данных за период 2015–2020 гг. Исследований дефолтов российских банков после 2015 г. сравнительно немного. Наша работа призвана восполнить этот пробел. Цель исследования состоит в выявлении переменных, статистически значимо влияющих на риск дефолта российских банков в условиях относительно стабильного развития российской экономики (2015–2020 гг.) без таких внешних шоков, как COVID‑19 или международные санкции. В работе используется комплексный подход к моделированию риска дефолтов банков. Модельный аппарат представлен логит-, пробит-моделями, а также регрессией Кокса. В качестве объясняющих переменных использовались индикаторы, характеризующие различные аспекты функционирования кредитных организаций (в соответствии с методологией CAMELS), а также макроэкономические переменные. Наиболее значимыми предикторами дефолта оказались норматив достаточности капитала Н1, чистые активы банка, отношение кредитного портфеля к активам, обеспеченность кредитного портфеля имуществом, отношение выданного количества межбанковских кредитов к активам, а также инфляция (INF) и цена закрытия индекса Московской биржи (MOEXIN). В целом полученные результаты согласуются с системой показателей устойчивости коммерческих банков CAMELS, при этом влияние общих макроэкономических показателей оказывается незначимым. Результаты исследования представляют интерес для регулятора в целях текущего надзора и предупреждения риска дефолта, самих кредитных организаций с целью построения внутренних систем мониторинга финансовой устойчивости и участников финансового рынка для выбора наиболее устойчивых компаний с точки зрения инвестирования и размещения средств. Дальнейшие направления исследования связаны с включением в анализ кризисного периода и сравнением значимых предикторов в кризис и в стабильный период развития экономики, а также с использованием альтернативных методов, в частности, алгоритмов машинного обучения.

This paper is devoted to modeling the probability of default of Russian banks in 2015–2020. There are relatively few studies on defaults of Russian banks after 2015, and our work intends to partly fill this gap. The purpose of this research is to determine the main variables which significantly impact the risk of default of Russian banks. The work seeks to identify additional factors associated with an increased risk of bank defaults during a relatively stable period of development of the Russian economy (2015–2020) without external shocks, such as COVID‑19 or international sanctions. We apply an integrated approach to modeling the risk of bank defaults. Empirical methodology is represented by logit and probit models, as well as Cox regression. The set of potential predictors for bank defaults include the variables, characterizing various aspects of credit institutions functioning (in accordance with the CAMELS system), as well as macroeconomic variables. The most significant predictors of default turn out to be the capital adequacy ratio N1, bank net assets, the ratio of total loans to assets and the size of secured loan portfolio. In general, the results we obtain are consistent with the CAMELS system of indicators assessing the sustainability of commercial banks, while the impact of macroeconomic indicators tends to be insignificant. The results of the study could be of interest to the regulator both for the purposes of ongoing monitoring of financial stability as well as for default risk prevention; to credit institutions which elaborate internal systems for monitoring their financial soundness; and to financial market participants to select the most stable companies in terms of investment and allocation of funds. Further directions of research are related to the inclusion of a crisis period into the analysis and comparing the set of significant predictors for bank defaults during a crisis and a stable period of economic development, as well as the use of alternative methods, in particular, machine learning algorithms.

банковский дефолткредитный рейтингCAMELSлогистическая регрессиярегрессия Коксаметоды машинного обученияbank defaultcredit ratingcamelslogistic regressioncoke regressionmachine learning methodsИсследование выполнено за счет гранта Российского научного фонда (проект № 23-18-00756).ReferencesАндреасян Г. (2000). Дистанционный анализ финансово-экономического состояния российских банков: Эконометрический подход: дис. ... канд. экон. наук: 08.00.13 М.: ЦЭМИ РАН. 140 с. URL: https://rsl.ruAndreasjan G. (2000). Remote Analysis of Financial and Economic Condition of Russian Banks: Econometric Approach: dis. ... Cand. Sc. (Economics): 08.00.13 Moscow: CEMI RAS. 140 p. (in Russian). URL: https://rsl.ruБиджоян Д., Богданова Т. (2017). Концепция моделирования и прогнозирования вероятности отзыва лицензий российских банков // Экономическая наука современной России. № 4 (79). С. 88–103.Bidzhojan D., Bogdanova T. (2017). The Concept of Modeling and Forecasting the Probability of Revoking a License of Russian Banks. Economics of Contemporary Russia, no. 4, pp. 88–102 (in Russian).Бывшев В., Прокопчина С., Мищенко С. (2021). Исследование дискриминационной способности финансовых коэффициентов ROA и ROE выявлять проблемные банки (российский опыт) // Мягкие измерения и вычисления. № 38 (1). С. 60–65.Byvshev V., Prokopchina S., Mishhenko S. (2021). Study of the Discriminatory Ability of ROA and ROE Financial Ratios to Identify Problem Banks (Russian Experience). Soft Measurements and Computing, no. 38 (1), pp. 60–65 (in Russian).Давыденко И., Козаченко Е. (2021). Возможности и границы использования модели бинарной логистической регрессии для оценки финансовой устойчивости и риска дефолта банка // Экономика устойчивого развития. № 1 (45). С. 141–145.Davydenko I., Kozachenko E. (2021). Possibilities and Limits of Using the Binary Logistic Regression Model for Assessing Financial Stability and the Risk of Bank Default. Economics of Sustainable Development, no. 1 (45), pp. 141–145 (in Russian).Зубарев А., Бекирова О. (2020). Анализ факторов банковских дефолтов 2013–2019 гг. // Экономическая политика. Т. 15. № 3. С. 106–133.Zubarev A., Bekirova O. (2020). Analysis of Bank Default Factors in 2013–2019. Economic Policy, vol. 15, no. 15 (3), pp. 106–133 (in Russian).Зубарев А., Шилов К. (2022). Дифференциация факторов банковских дефолтов по причинам отзыва лицензий // Экономический журнал ВШЭ. № 26 (1). С. 69–103.Zubarev A., Shilov K. (2022). Bank default's differentiation based on license withdrawal reasons. HSE Economic Journal, no. 26 (1), pp. 69–103 (in Russian).Карминский А. М., Пересецкий А. А., Петров А. Е. (2005). Рейтинги в экономике: методология и практика. М: Финансы и статистика. 470 c.Karminsky A. M., Peresetsky A. A., Petrov A. E. (2005). Ratings in Economics: Methodology and Practice. Moscow: Finance and Statistics. 470 p. (in Russian).Карминский А. М., Костров А. В. (2013). Моделирование вероятности дефолта российских банков: расширенные возможности // Журнал Новой экономической ассоциации. № 1 (17). С. 64–70.Karminsky A. M., Kostrov A. V. (2013). Modeling the Default Probabilities of Russian Banks: Extended Abilities. The Journal of the New Economic Association. No. 1(17), pp. 64–70 (in Russian).Класс Я., Класс Т. (2018). Идентификация факторов риска банкротства кредитных организаций и их моделирование // Финансы и кредит. № 24(1). С. 19–32.Klass Ja., Klass T. (2018). Identification of Risk Factors of Bankruptcy of Credit Institutions and Their Modelling. Finance and Credit, no. 24(1), pp. 19–32 (in Russian).Пересецкий А. А. (2013). Модели причин отзыва лицензий российских банков. Влияние неучтенных факторов // Прикладная эконометрика. № 30 (2). С. 49–64.Peresecky A. A. (2013). Modeling Reasons for Russian Bank License Withdrawal: Unaccounted Factors. Applied Econometrics, no. 30 (2), pp. 49–64 (in Russian).Радионова М., Приступина Ю. (2017). Моделирование вероятности дефолта российских банков // Финансовая аналитика: теория и практика. № 10 (2). С. 226–240.Radionova M., Pristupina Ju. (2017). Modeling the probability of default of Russian banks. Financial Analytics: Science and Experience, no. 10 (2), pp. 226–240 (in Russian).Синельникова-Мурылева Е., Горшкова Т., Макеева Н. (2018). Прогнозирование дефолтов в российском банковском секторе // Экономическая политика. Т. 13. № 2. С. 8–27.Sinelnikova-Muryljova E., Gorshkova T., Makeeva N. (2018). Default Forecasting in the Russian Banking Sector. Economic Policy, vol. 13, no. 2, pp. 8–27 (in Russian).Тотьмянина К. М. (2011). Обзор моделей вероятности дефолта // Управление финансовыми рисками. № 1. С. 12–24.Totmjanina K. M. (2011). Overview of models of default probability. Financial Risk Management Journal, no. 1, pp. 12–24 (in Russian).Хасянова С., Цыганова В. (2018). Качество риск-менеджмента в банке: предпосылки возникновения финансовых проблем // Российский журнал менеджмента. № 16 (2). С. 187–204.Hasjanova S., Cyganova V. (2018). The Quality of Bank Risk Management: Triggers of Financial Problems. Russian Management Journal, no. 16 (2), pp. 187–204 (in Russian).Широбокова М. А. (2018). Модель оценки риска дефолта на всем протяжении жизни кредита // Вестник Удмуртского университета. Серия «Экономика и право». № 28(2). С. 228–233.Shirobokova M. (2018). Model of Evaluating the Default Credit Risk throughout the Whole Life of the Loan. Bulletin of Udmurt University. Series “Economics and Law”, no. 28(2), pp. 228–233 (in Russian).Яшина Н., Макарова С., Макаров И. и др. (2017). Прогнозирование дефолта коммерческих банков на основе вероятностной модели // Экономический анализ: теория и практика. № 16 (12 (471)). С. 2376–2391.Jashina N., Makarova S., Makarov I., et al. (2017). Forecasting the Commercial Bank Default Based on a Probabilistic Model. Economic Analysis: Theory and Practice, no. 16, vol. 12 (471), 2376–2391 (in Russian).Albulescu C. (2022). Bank Financial Stability and International Oil Prices: Evidence from Listed Russian Public Banks. Eastern European Economics, vol. 60(3), pp. 217–246.Albulescu C. (2022). Bank Financial Stability and International Oil Prices: Evidence from Listed Russian Public Banks. Eastern European Economics, vol. 60(3), pp. 217–246.Altman E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance, no. 23(4), pp. 589–609.Altman E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance, no. 23(4), pp. 589–609.Altman E. I., Marco G., Varetto F. (1994). Corporate distress diagnosis: comparisons using linear discriminant analysis and neural networks (the Italian experience). Journal of Banking and Finance, no. 18 (3), pp. 505–529.Altman E. I., Marco G., Varetto F. (1994). Corporate distress diagnosis: comparisons using linear discriminant analysis and neural networks (the Italian experience). Journal of Banking and Finance, no. 18 (3), pp. 505–529.Avery R. B., Hanweck G. A. (1984). A dynamic analysis of bank failures. Board of Governors of the Federal Reserve System, no. 74.Avery R. B., Hanweck G. A. (1984). A dynamic analysis of bank failures. Board of Governors of the Federal Reserve System, no. 74.Barajas A., Krakovich V., Lopez-Iturriaga F. (2023). Survival of Russian Banks: How Efficient are the Control Measures? European Journal of Management and Business Economics, vol. 32, no. 3, pp. 320–341.Barajas A., Krakovich V., Lopez-Iturriaga F. (2023). Survival of Russian Banks: How Efficient are the Control Measures? European Journal of Management and Business Economics, vol. 32, no. 3, pp. 320–341.Bigus J. P. (1996). Data mining With Neural Networks: Solving Business Problems from Application Development to Decision Support. Hightstown: McGraw-Hill, Inc.Bigus J. P. (1996). Data mining With Neural Networks: Solving Business Problems from Application Development to Decision Support. Hightstown: McGraw-Hill, Inc.Bondarenko M., Semenova M. (2018). Do High Deposit Interest Rates Signal Bank Default? Evidence from the Russian Retail Deposit Market. National Research University “Higher School of Economics”. HSE Working Paper, no. BRP 65/FE/2018.Bondarenko M., Semenova M. (2018). Do High Deposit Interest Rates Signal Bank Default? Evidence from the Russian Retail Deposit Market. National Research University “Higher School of Economics”. HSE Working Paper,Bräuning M., Malikkidou D., Scalone S., et al. (2019). A New Approach to Early Warning Systems for Small European Banks. ECB Working Paper, no. 2348.no. BRP 65/FE/2018.Carree M. (2003). A Hazard Rate Analysis of Russian Commercial Banks in the Period 1994–1997. Economic Systems, no. 27(3), pp. 255–269.Bräuning M., Malikkidou D., Scalone S., et al. (2019). A New Approach to Early Warning Systems for Small European Banks. ECB Working Paper, no. 2348.Chan-Lau J.A. (2006). Fundamentals-based estimation of default probabilities: a survey. IMF Working Paper, no. 149.Carree M. (2003). A Hazard Rate Analysis of Russian Commercial Banks in the Period 1994–1997. Economic Systems, no. 27(3), pp. 255–269.Chernykh L., Kotomin V. (2022). Risk-based Deposit Insurance, Deposit Rates and Bank Failures: Evidence from Russia. Journal of Banking and Finance, vol. 138, article 106438.Chan-Lau J.A. (2006). Fundamentals-based estimation of default probabilities: a survey. IMF Working Paper, no. 149.Chernykh L., Mityakov S. (2022). Behaviour of Corporate Depositors during a Bank Panic. Management Science, vol. 68 (12), pp. 9129–9159.Chernykh L., Kotomin V. (2022). Risk-based Deposit Insurance, Deposit Rates and Bank Failures: Evidence from Russia. Journal of Banking and Finance, vol. 138, article 106438.Erdogan B. (2013). Prediction of Bankruptcy Using Support Vector Machines: An Application to Bank Bankruptcy. Journal of Statistical Computation and Simulation, vol. 83 (8), pp. 1543–1555.Chernykh L., Mityakov S. (2022). Behaviour of Corporate Depositors during a Bank Panic. Management Science, vol. 68 (12), pp. 9129–9159.Fungáčová Z., Solanko L. (2009). Risk-Taking by Russian Banks: Do Location, Ownership and Size Matter? Bank of Finland. Institute for Economies in Transition. BOFIT Discussion Papers 21.Erdogan B. (2013). Prediction of Bankruptcy Using Support Vector Machines: An Application to Bank Bankruptcy. Journal of Statistical Computation and Simulation, vol. 83 (8), pp. 1543–1555.Fungáčová Z., Turk R., Weill L. (2021). High Liquidity Creation and Bank Failures. Journal of Financial Stability, vol. 57, 100937.Fungáčová Z., Solanko L. (2009). Risk-Taking by Russian Banks: Do Location, Ownership and Size Matter? Bank of Finland. Institute for Economies in Transition. BOFIT Discussion Papers 21.Fungáčová Z., Weill L. (2013). Does Competition Influence Bank Failures? Evidence from Russia. Economics of Transition and Institutional Change, vol. 21, no. 2, pp. 301–322.Fungáčová Z., Turk R., Weill L. (2021). High Liquidity Creation and Bank Failures. Journal of Financial Stability, vol. 57, 100937.Jing Z., Fang Y. (2018). Predicting US Bank Failures: A Comparison of Logit and Data Mining Models. Journal of Forecasting, vol. 37 (2), pp. 235–256.Fungáčová Z., Weill L. (2013). Does Competition Influence Bank Failures? Evidence from Russia. Economics of Transition and Institutional Change, vol. 21, no. 2, pp. 301–322.Karminsky A., Kostrov A. (2016). The Back Side of Banking in Russia: Forecasting Bank Failures with Negative Capital. International Journal of Computational Economics and Econometrics, vol. 7, no. 1–2, pp. 170–209.Jing Z., Fang Y. (2018). Predicting US Bank Failures: A Comparison of Logit and Data Mining Models. Journal of Forecasting, vol. 37 (2), pp. 235–256.Kočenda E., Iwasaki I. (2022). Bank Survival around the World: A Meta-analytic Review. Journal of Economic Surveys, vol. 36 (1), pp. 108–156.Karminsky A., Kostrov A. (2016). The Back Side of Banking in Russia: Forecasting Bank Failures with Negative Capital. International Journal of Computational Economics and Econometrics, vol. 7, no. 1–2, pp. 170–209.Lanine G., Vennet R. (2006). Failure Prediction in the Russian Bank Sector with Logit and Trait Recognition Models. Expert Systems with Applications, vol. 30 (3), pp. 463–478.Kočenda E., Iwasaki I. (2022). Bank Survival around the World: A Meta-analytic Review. Journal of Economic Surveys, vol. 36 (1), pp. 108–156.Makinen, M., Solanko L. (2018). Determinants of Bank Closures: Do Levels or Changes of CAMEL Variables Matter? Russian Journal of Money and Finance, vol. 77(2), pp. 3–21.Lanine G., Vennet R. (2006). Failure Prediction in the Russian Bank Sector with Logit and Trait Recognition Models. Expert Systems with Applications, vol. 30 (3), pp. 463–478.Martin D. (1977). Early Warning of Bank Failure: A Logit Regression Approach. Journal of Banking & Finance, vol. 1, pp. 249–276.Makinen, M., Solanko L. (2018). Determinants of Bank Closures: Do Levels or Changes of CAMEL Variables Matter? Russian Journal of Money and Finance, vol. 77(2), pp. 3–21.Orbe J., Núñez-Antón V. (2011) Analysis of the Determinants of Survival for the Russian Commercial Banking Industry: A New Approach. Applied Stochastic Models in Business and Industry, vol. 27 (3), pp. 301–314.Martin D. (1977). Early Warning of Bank Failure: A Logit Regression Approach. Journal of Banking & Finance, vol. 1, pp. 249–276.Peresetsky A. A., Karminsky A. M., Golovan S. V. (2011) Probability of Default Models of Russian Banks. Economic Change and Restructuring, vol. 44, no. 4.Orbe J., Núñez-Antón V. (2011) Analysis of the Determinants of Survival for the Russian Commercial Banking Industry: A New Approach. Applied Stochastic Models in Business and Industry, vol. 27 (3), pp. 301–314.Philippon, T., Wang O. (2023). Let the Worst One Fail: A Credible Solution to the Too-Big-To-Fail Conundrum. Quarterly Journal of Economics, vol. 138 (2), pp. 1233–1271.Peresetsky A. A., Karminsky A. M., Golovan S. V. (2011) Probability of Default Models of Russian Banks. Economic Change and Restructuring, vol. 44, no. 4.Ploeg S. (2010). Bank Default Prediction Models: A Comparison and an Application to Credit Rating Transitions. Ernst & Young – ​Financial Services Risk Management. Rotterdam: Erasmus University.Philippon, T., Wang O. (2023). Let the Worst One Fail: A Credible Solution to the Too-Big-To-Fail Conundrum. Quarterly Journal of Economics, vol. 138 (2), pp. 1233–1271.Shibitov D., Mamedli M. (2019). The Finer Points of Model Comparison in Machine Learning: Forecasting Based on Russian Banks’ Data. Bank of Russia Working Paper, no. 43. August.Ploeg S. (2010). Bank Default Prediction Models: A Comparison and an Application to Credit Rating Transitions. Ernst & Young – ​Financial Services Risk Management. Rotterdam: Erasmus University.Tamari M. (1966). Financial ratios as a means of forecasting bankruptcy. Management International Review, no. 4, pp.15–21.Shibitov D., Mamedli M. (2019). The Finer Points of Model Comparison in Machine Learning: Forecasting Based on Russian Banks’ Data. Bank of Russia Working Paper, no. 43. August.Tankoeva V., Bazzana F., Gabriele R. (2018). The Stability of the Financial System: An Analysis of Russian Bank Failures. In: Research Handbook of Investing in the Triple Bottom Line: Finance, Society and Environment. Ed. by S. Boubaker, D. Cumming, D. K. Nguyen. Cheltenham (UK), Northampton (USA): Edward Elgar.Tamari M. (1966). Financial ratios as a means of forecasting bankruptcy. Management International Review, no. 4, pp.15–21.Wilson T. (1997). Portfolio Credit Risk: Part I. Risk Magazine, September.Tankoeva V., Bazzana F., Gabriele R. (2018). The Stability of the Financial System: An Analysis of Russian Bank Failures. In: Research Handbook of Investing in the Triple Bottom Line: Finance, Society and Environment. Ed. by S. Boubaker, D. Cumming, D. K. Nguyen. Cheltenham (UK), Northampton (USA): Edward Elgar.Wilson T. (1997). Portfolio Credit Risk: Part I. Risk Magazine, September.Wilson T. (1997). Portfolio Credit Risk: Part I. Risk Magazine, September.

The authors declare that there are no conflicts of interest present.