MODEL FOR ASSESSING THE PROBABILITY OF REVOCATION OF A LICENSE FROM THE RUSSIAN BANK

The article deals with the problem of modeling and forecasting the revocation of the bank’s license depending on the volatility of macroeconomic variables. The urgency of this problem is due to the following reasons. First, the Central Bank of theRussian Federationtoday pursues a policy of clearing the banking sector from unscrupulous participants in the banking market and from banks with weak economic positions. Secondly, the strong fl in the values of macroeconomic variables over the previous few years affect the financial condition of the bank, which is the basis for the decision to revoke the license. The purpose of the article is to develop a model for assessing the probability of revocation of a license from the Russian bank on the basis of its public financial statements, taking into account the volatility of macroeconomic variables. The author has developed a logistic regression model for assessing the probability of revocation of a license from the Russian bank taking into account the volatility of macroeconomic variables. To level the effect of multicollinearity in the data, we use RIDGE modification of the logistic regression model with a certain algorithm for setting the penalty factor. The model is based on the data of official public bank statements, data on macroeconomic variables, and data on license revocations by the Bank of Russia as well. To aggregate the information and bring it into a single format, an information and logical model for the formation of the information base of the study is developed. The obtained model for assessing the probability of revocation of a license from the Russian bank has a high prognostic ability. The hypothesis of statistical difference of coefficients from zero is accepted when indicators of volatility of macroeconomic variables were at significance levels of 0.01 and above. The author concluded that the volatility of macroeconomic variables has a significant impact on the fi condition of the bank. The Bank of Russia takes this into account when deciding whether to revoke a license, as the fi condition is one of the key aspects. This approach can be used by the bank’s counterparties in assessing its reliability. 

1. Egorova O. Yu. Classification of approaches, models and diagnostic methods of bank bankruptcy. Global’nye rynki i finansovyy inzhiniring = Global Markets and Financial Engineering. 2015;2(3):229–244. DOI: 10.18334/grfi.2.3.1916 (In Russ.)

2. Fungasova Z., Turk R., Weill L. High liquidity creation and bank failures. IMF Working Paper. 2015;(103). URL: https://www.imf.org/external/pubs/ft/wp/2015/wp15103.pdf (accessed 11.04.2018).

3. Gurny P., Gurny M. Comparison of credit scoring models on probability of default estimation of US banks. Prague Economic Papers. 2013;22(2):163–181. DOI: https://doi.org/10.18267/j.pep.446

4. Babajide A.A., Olokoyo F.O., Adegboye F.B. Predicting bank failure in Nigeria using survival analysis approach. Journal of South African Business Research. 2015; Article ID 965940. DOI: 10.5171/2015.965940 URL: http://eprints.covenantuniversity.edu.ng/5427/1/Dr%20Adegboye%20F.%20B%202.pdf (accessed 11.04.2018).

5. Karminsky A., Kostrov A. The back side of banking in Russia: Forecasting bank failures with negative capital. International Journal of Computational Economics and Econometrics. 2017;7(1/2):170–209. DOI: 10.1504/ijcee.2017.10000658

6. Calabrese R., Giudici P. Estimating bank default with generalised extreme value models. DEM Working Paper Series. 2013;(35). URL: ftp://ftp.repec.org/opt/ReDIF/RePEc/pav/demwpp/DEMWP0035.pdf (accessed 11.04.2018).

7. Tot’myanina K.M. Probability of default models for corporates taking into account macroeconomic situation. Korporativnye finansy = Journal of Corporate Finance Research. 2014;(1):18–30. (In Russ.).

8. Peresetsky A. Models of reasons for revocation of licenses of Russian banks. New Economic School. Preprint. 2010;(085). URL: https://www.nes.ru/dataupload/files/programs/econ/preprints/2010/Peresetsky_2010.pdf (accessed 11.04.2018). (In Russ.).

9. Karminsky A.M., Kostrov A.V., Murzenkov T.N. Bank’s default probability and its modeling. Finansovaya analitika: problemy i resheniya = Financial Analytics: Science and Experience. 2012;5(41):2–13. (In Russ.).

10. Karminsky A., Kostrov A. The probability of default in Russian banking. Eurasian Economic Review. 2014;4(1):81–98. DOI: 10.1007/s40822–014–0005–2

11. Karminsky A.M. Is it necessary to regulate credit rating agencies? Global’nye rynki i finansovyi inzhiniring = Global Markets and Financial Engineering. 2014;1(1):25–34. DOI: 10.18334/grfi.1.1.6 (In Russ.).

12. Peresetsky A.A. Econometric methods in remote analysis of Russian banks. Moscow: Publishing House of the Higher School of Economics; 2012. 235 p. (In Russ.).

13. Karminsky A.M., Sosyurko V.V. Comparison of bank credit ratings for various agencies. Zhurnal novoi ekonomicheskoi assotsiatsii = Journal of the New Economic Association. 2011;(12):102–123. (In Russ.).

14. Livingston M., Wei J., Zhou L. Moody’s and S&P ratings: Are they equivalent? Conservative ratings and split rated bond yields. Journal of Money, Credit and Banking. 2010;42(7):1267–1293. DOI: 10.1111/j.1538–4616.2010.00341.x

15. Zhivaikina A.D., Peresetsky A.A. Russian banks credit ratings and bank licenses revocations 2012–2016. Zhurnal novoi ekonomicheskoi assotsiatsii = Journal of the New Economic Association. 2017;(4):49–80. (In Russ.).

16. Bidzhoyan D.S. The approach to forecasting the financial condition of an enterprise taking into account changes in macroeconomic indicators. Audit i finansovyi analiz. 2016;(4):195–200. (In Russ.).

17. Bidzhoyan D.S., Bogdanova T.K. Modelling the financial stability of an enterprise taking into account macroeconomic indicators. Business Informatics. 2016;(3):30–37 р. DOI: 10.17323/1998–0663.2016.3.30.37

18. Aguilera A.M., Escabias M., Valderrama M.J. Using principal components for estimating logistic regression with high-dimensional multicollinear data. Computational Statistics & Data Analysis. 2006;50(8):1905–1924. DOI: 10.1016/j.csda.2005.03.011

19. Cule E., Vineis P., De Iorio M. Significance testing in ridge regression for genetic data. BMC Bioinformatics. 2011;12(1):372. DOI: 10.1186/1471–2105–12–372

20. Calabrese R. Optimal cut-off for rare events and unbalanced misclassification costs. Journal of Applied Statistics. 2014;41(8):1678–1693. DOI: 10.1080/02664763.2014.888542