Subject. The article deals with the development of advanced risk assessment method for retail investment products (mutual funds, ETFs, and structured notes) purchased on the Russian stock market. Objectives. The main goal is to create a qualitative stress testing model that takes into account the interdependence of risk factors. Methods. The study employs machine learning modeling, in particular, the vector error correction model (VECM) method enabling to take into account the non-stationarity of time series and cointegration relationships between macroeconomic indicators. Statistical tests for stationarity, multicollinearity, and cointegration were conducted to select the factors. We applied the cross-validation approach and calculation of the forecast error using the MAPE metric. Results. We selected and trained a model based on the vector error correction model method. It helped consider the non-stationarity of time series and interrelationship of risk factors, which made the estimates of other models incorrect. The final mean absolute percentage error was 19.41%, which means that the forecast is highly accurate. The risk factors involved in the modeling were inflation [1] (both food basket and wages), exchange rates, oil and the key rate, given their mutual influence on each other [2]. Conclusions. The offered method will enable a deeper and more comprehensive stress test of retail investment products based on the vector error correction model machine learning method. The integrated approach to assessing risk factors will increase investor protection by better informing about the maximum level of losses under adverse market conditions.
Kobrinskaya O.G. [Content and stages of stress testing of financial risks of the enterprise]. Vestnik Polotskogo gosudarstvennogo universiteta. Seriya D. Ekonomicheskie i yuridicheskie nauki = Bulletin of Polotsk State University. Series D. Economic and Legal Sciences, 2020, no. 6, pp. 79–85. (In Russ.) EDN: GHITLR
Kerzhakov N.V. [Time series and requirements for them]. Ekonomika i sotsium = Economics and Society, 2022, no. 11-2, pp. 450–453. (In Russ.) EDN: MNTLUD
Moiseev N.A. [Comparative analysis of efficiency methods of elimination of multicollinearity]. Uchet i statistika = Accounting and Statistics, 2017, no. 2, pp. 62–73. (In Russ.) EDN: ZELDIN
Mamonov M.E. [Market for retail loans in Russia: The identification of demand and supply through the VECM approach]. Ekonomicheskii zhurnal Vysshei shkoly ekonomiki = HSE Economic Journal, 2017, vol. 21, no. 2, pp. 251–282. (In Russ.) EDN: ZFVTSV
Danilova E.O., Markov K.V. [Macroprudential stress-testing of the financial sector: International experience and the Bank of Russia’s approaches]. Den'gi i kredit = Russian Journal of Money and Finance, 2017, no. 10, pp. 3–15. (In Russ.) EDN: ZIZVUP
Katyukha P.B. [Global oil market on price redistribution threshold]. Rossiiskii vneshneekonomicheskii vestnik = Russian Foreign Economic Bulletin, 2020, no. 2, pp. 119–132. (In Russ.) URL: Link
Mikheeva E.A., Chernyaev V.A. [Analysis of the dynamics of the key rate and its interrelations with macroeconomic indicators]. Ekonomika i biznes: teoriya i praktika = Economy and Business: Theory and Practice, 2023, no. 10-2 S. 78–83. (In Russ.) EDN: ILVBMZ
Meshkova E.I. [Modern trends and problems of interest rate policy of banks]. Finansovye rynki i banki = Financial Markets and Banks, 2023, no. 6, pp. 112–116. (In Russ.) EDN: MOLAPC
Shlychkov V.V., Nestulaeva D.R., Zareznov D.A. [Russia’s economy in 2022: Challenges and mechanisms to overcome them]. Vestnik Chelyabinskogo gosudarstvennogo universiteta = Bulletin of Chelyabinsk State University, 2023, no. 3, pp. 240–249. (In Russ.) EDN: XXQTKM
Pavlova G.G. [Some modern problems of wage indexation in conditions of increasing inflation]. Vestnik ekonomiki, upravleniya i prava = Bulletin of Economics, Management and Law, 2023, vol. 16, no. 4, pp. 29–36. (In Russ.) EDN: TWWUAX
Shekshueva S.V. [Stress testing of modern commercial banks in Russia]. Sovremennye naukoemkie tekhnologii. Regional'noe prilozhenie = Modern Science-Intensive Technologies. Regional Application, 2022, no. 4, pp. 27–32. (In Russ.) EDN: ORQWPJ
Bidzhoyan D.S., Bogdanova T.K., Neklyudov D.Yu. [Credit risk stress testing in a cluster of Russian commercial banks]. Biznes-informatika = Business Informatics, 2019, vol. 13, no. 3, pp. 35–51. (In Russ.) EDN: UIQCEO
Kozyr' N.S., Epranosyan A.A. [Stress testing as a method for analyzing banking risks]. Finansovaya analitika: problemy i resheniya = Financial Analytics: Problems and Solutions, 2015, no. 22, pp. 31–44. URL: Link (In Russ.)
Shamrina S.Yu., Lomakina A.N. [A scenario analysis of stress testing in the assessment of the main risks of a credit institution]. Daidzhest-finansy = Digest Finance, 2021, vol. 26, no. 2, pp. 212–229. (In Russ.) URL: Link
