Subject. The article addresses the selection of informative and significant regional determinants of economic security. Objectives. The aim is to explore statistical and econometric tools to select regional determinants, to build economic security classifiers, using the machine learning algorithms. Methods. The determinants are selected, using the filter-based methods (on the basis of Chi-square, F-criterion, information content criterion), sequential and recursive selection in the opposite direction, exhaustive sampling and selection based on the "random forest" classifier. The above algorithms are implemented in the Scikit-learn and MLxtend libraries. The analytical environment Jupyter Notebook is used as a system providing the execution of feature selection algorithms. Results. I formed a training sample of 90% of the total set of regional economic determinants for 82 Russian regions. The determinants were ranked by significance. Logistic loss and model accuracy were set as a model evaluation criterion. The accuracy of created classifiers was between 78% and 93%. The paper establishes the significance of categorical variables that determine whether a particular region belongs to the resource, investment, or regional profitability cluster. The constructed heat map enabled to establish the degree of linear relationship between the level of economic security of the region and regional determinants. Conclusions. The most significant group of panel indicators to determine the class of economic security is the resource security of regions. The level of resource endowment depends on the volume of consumption and the share of manufactured goods in the GRP. To build a model to classify regions by the economic security level, five features are sufficient; this circumstance was established by automatic set of determinants, using the recursive feature elimination algorithm with cross-validation (RFECV). The implemented wrapping methods of feature selection demonstrated that significant indicators in the model are budget expenditures and the amount of debt per capita, investment risk and net financial result. The best quality of the classifier is provided in the course of an exhaustive set of features, using the K-Nearest Neighbors algorithm.
Keywords: economic security, selection of economic determinants, filtration method, wrapper method, region
References:
Shutaeva E.A., Pobirchenko V.V. [Investment security threats from perspectives of the economic security of the Russian Federation]. Natsional'nye interesy: prioritety i bezopasnost' = National Interests: Priorities and Security, 2018, vol. 14, iss. 8, pp. 1498–1513. (In Russ.) URL: Link
Nozhkina E.B. [Some aspects of the system of ensuring investment security]. Vestnik Saratovskogo gosudarstvennogo sotsial'no-ekonomicheskogo universiteta = Vestnik of Saratov State Socio-Economic University, 2017, no. 5, pp. 101–103. URL: Link (In Russ.)
Nazarov A.I. [Influence of the investment climate on the economic security of the State]. Ekonomicheskaya bezopasnost' = Economic Security, 2019, vol. 2, no. 3, pp. 255–263. URL: Link (In Russ.)
Khadisov M.-R.B. [Methods for assessing the level of the region's economic security: A comparative analysis]. Natsional'nye interesy: prioritety i bezopasnost' = National Interests: Priorities and Security, 2015, no. 33, pp. 31–44. URL: Link (In Russ.)
Shakleina M.V., Midov A.Z. [Strategic classification of regions according to the level of financial self-sufficiency]. Ekonomicheskie i sotsial'nye peremeny: fakty, tendentsii, prognoz = Economic and Social Changes: Facts, Trends, Forecast, 2019, vol. 12, no. 3, pp. 39–54. URL: Link (In Russ.)
Gubanova E.S., Moskvina O.S. [Methodological aspects of the assessment of the investment and innovation potential of a region]. Ekonomicheskie i sotsial'nye peremeny: fakty, tendentsii, prognoz = Economic and Social Changes: Facts, Trends, Forecast, 2020, vol. 13, no. 2, pp. 41–55. URL: Link (In Russ.)
Malkina M.Yu., Balakin R.V. Nalogovaya sistema Rossiiskoi Federatsii i ee kharakteristiki: monografiya [Tax system of the Russian Federation and its characteristics: a monograph]. Moscow, INFRA-M Publ., 2019, 127 p.
Pechenskaya M.A. [Budget capacity in the system of capacities of the territory: Theoretical issues]. Ekonomicheskie i sotsial'nye peremeny: fakty, tendentsii, prognoz = Economic and Social Changes: Facts, Trends, Forecast, 2018, vol. 11, no. 5, pp. 61–73. URL: Link (In Russ.)
Maslennikov D.A., Mityakov S.N., Kataeva L.Yu., Fedoseeva T.A. [Identification of the Characteristics of the Regional Strategic Development Based on the Indicators’ Statistical Analysis]. Ekonomika regiona = Economy of Region, 2019, vol. 15, iss. 3, pp. 707–719. URL: Link (In Russ.)
Beklaryan G.L. [Decision support system for sustainable economic development of the Far Eastern Federal District]. Biznes-informatika = Business Informatics, 2018, no. 4, pp. 66–75. URL: Link (In Russ.)
Leshchenko Yu.G. [Innovative vector in the system of economic security of Russia]. Voprosy innovatsionnoi ekonomiki = Russian Journal of Innovation Economics, 2019, vol. 9, no. 2, pp. 301–316. URL: Link (In Russ.)
Rumyantsev A.A. [Research and Innovation Activity in the Region as a Driver of Its Sustainable Economic Development]. Ekonomicheskie i sotsial'nye peremeny: fakty, tendentsii, prognoz = Economic and Social Changes: Facts, Trends, Forecast, 2018, vol. 11, no. 2, pp. 84–99. URL: Link (In Russ.)
Belyanichev V.G., Savderova A.F. [Assessment of the impact of real fixed capital formation on the volume of the gross regional product]. Oeconomia et Jus, 2019, no. 1. (In Russ.) URL: Link
Sinel'nikova-Muryleva E.V., Gorshkova T.G., Makeeva N.V. [Default Forecasting in the Russian Banking Sector]. Ekonomicheskaya politika, 2018, vol. 13, no. 2. URL: Link (In Russ.)
Galazova S.S. [Influence of ESG-factors on sustainable development of companies and financial performance of corporate sector]. Vestnik Rostovskogo gosudarstvennogo ekonomicheskogo universiteta = Vestnik of Rostov State University of Economics, 2018, no. 4, pp. 81–86. URL: Link (In Russ.)
Erokhin S.D., Borisenko B.B., Martishin I.D., Fadeev A.S. [Analysis of existing methods to reduce the dimensionality of input data]. T-Comm, 2022, vol. 16, no. 1, pp. 30–37. URL: Link (In Russ.)
Gareev M.Yu. [Use of Machine Learning Methods to Forecast Investment in Russia]. Den'gi i kredit = Russian Journal of Money & Finance, 2020, no. 1, pp. 35–56. URL: Link (In Russ.)
