Home  Journals  Financial Analytics: Science and Experience  1(367) - 2024 January-March

Machine learning tools in the tasks of selecting the determinants of socio-economic situation and development potential of Russian regions

Received: 7 September 2023

Received in revised form: 20 September 2023

Accepted: 13 October 2023

Available online: 29 February 2024

Subject Heading: MATHEMATICAL ANALYSIS AND MODELING IN ECONOMICS

JEL Classification: C15, C38, E17, R13, R15

Pages: 37–55

https://doi.org/10.24891/fa.17.1.37

Subject. The article addresses the selection of determinants that are significant for assessing the level of socio-economic situation and development potential of Russian regions.
Objectives. The aim is to study machine learning algorithms for the selection of determinants – predictors of the level of socio-economic situation and development potential of Russian regions, to build models of classification of regions, according to the level of socio-economic situation, using various machine learning algorithms.
Methods. To build classification models, I used data from the Federal State Statistics Service, the Institute of Scientific Communications, the RIA Novosti news agency, and the TAdviser Internet portal. Procedures for data classification, model parameter estimation, selection of significant determinants and visualization of results are performed, using the basic functions of the PyCaret library. Cohen's Kappa statistics and Matthews correlation coefficient were employed as priority metrics for evaluating the model productivity. The algorithms for selecting determinants are implemented in the Google Colab analytical environment.
Results. I constructed multiclass classification models based on simple and ensemble machine learning algorithms. Simple classification algorithms, including logistic and ridge regression models, naive Bayesian algorithm, decision tree, support vector machine, and k-nearest neighbor methods are characterized by accuracy values at 77%, however, Cohen's Kappa statistics and the Matthews correlation coefficient only show a satisfactory relationship between the actual and predicted value of the region class. Ensemble algorithms, including random forest, gradient boosting and extreme gradient boosting, are characterized by a close relationship between the actual and forecast estimates of the classifier at a level of more than 70%.
Conclusions. The random forest algorithm is recognized as the most effective classification model. The gross regional product and investments in fixed assets are informative determinants for measuring the socio-economic status.

Keywords: region, socio-economic situation, potential, classification, ensemble algorithm

References:

1. Egorov N.E., Kovrov G.S., Tishkov S.V., Volkov A.D. [The potential of digitalization of resource regions of the Russian North]. MIR (Modernizatsiya. Innovatsii. Razvitie) = MIR (Modernization. Innovation. Research), 2022, vol. 13, no. 2, pp. 238–251. URL: Link (In Russ.)
2. Kurbatova M.V., Levin S.N., Kagan E.S., Kislitsyn D.V. [Resource-type regions in Russia: Definition and classification]. Terra Economicus, 2019, vol. 17, no. 3, pp. 89–106. URL: Link (In Russ.)
3. 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.)
4. 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, no. 2, pp. 21–55. URL: Link metodologicheskie-aspekty-otsenki-investitsionno-innovatsionnogo-potentsiala-regiona?ysclid=lndjmh09z3770669973 (In Russ.)
5. Merkulova E.Yu., Spiridonov S.P., Men'shchikova V.I. [Indicators for evaluating the living standards in Russian regions]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2018, vol. 17, iss. 11, pp. 2066–2090. (In Russ.) URL: Link
6. Kurkin V.A. [Analysis of the dynamics of the development of the digital economy in the regions of Russia]. Regional'naya ekonomika i upravlenie: elektronnyi nauchnyi zhurnal, 2020, no. 4. (In Russ.) URL: Link
7. Turko T.I., Popikov D.N., Kruchak N.A. [Rating of innovative development of the subjects of the Russian Federation: Statistical evaluation]. Innovatika i ekspertiza = Innovatics and Expert Examination, 2022, no. 2, pp. 31–41. URL: Link (In Russ.)
8. Kaurova O.V., Maloletko A.N., Matraeva L.V., Korol'kova N.A. [Determining the composition of indicators assessment of the level of digital economy development in the region (regional digital environment)]. Fundamental'nye i prikladnye issledovaniya kooperativnogo sektora ekonomiki = Fundamental and Applied Researches of the Cooperative Sector of the Economy, 2020, no. 1, pp. 138–149. URL: Link 9dbb8b1e2727fc0c8b0de118c28afaaa.pdf (In Russ.)
9. Sadyrtdinov R.R. [The level of digitalization of the regions of Russia]. Vestnik Chelyabinskogo gosudarstvennogo universiteta = Bulletin of Chelyabinsk State University, 2020, no. 10, pp. 230–235. URL: Link (In Russ.)
10. Kvasnikova M.A. [Digital inequality and its impact on the socio-economic development of regions in Russia]. Sotsial'no-politicheskie issledovaniya = Social and Political Research, 2020, no. 1, pp. 43–58. URL: Link (In Russ.)
11. Derkachenko O.V. [Multidimensional analysis of Russia's regions on the level of development of the digital economy]. Uchet i statistika = Accounting and Statistics, 2021, no. 2, pp. 84–91. URL: Link (In Russ.)
12. Batrakova L.G. [Development of digital economy in Russian regions]. Sotsial'no-politicheskie issledovaniya = Social and Political Research, 2019, no. 1, pp. 45–60. URL: Link (In Russ.)
13. Afanas'eva T.V., Kazanbieva A.Kh. [Approach to Assessing the Digital Economy Development Based on Clustering of Russian Regions]. Ekonomika regiona = Economy of Regions, 2022, vol. 18, iss. 4, pp. 1075–1088. (In Russ.) URL: Link
14. Malkina M.Yu., Zakharov V.Ya., Granitsa Yu.V. et al. Ustoichivoe razvitie ekonomiki Rossii [Sustainable development of the Russian economy]. Moscow, Rusains Publ., 2022, 172 p.
15. Mityakov S.N., Mityakov E.S. [Machine learning in research tasks innovative processes]. Zhurnal prikladnykh issledovanii = Journal of Applied Research, 2020, no. 4, pp. 6–13. URL: Link (In Russ.)
16. Sakhanevich D.Yu. [Research of approaches and methods of applying artificial intelligence and machine learning in socio-economic processes]. Vestnik Omskogo universiteta. Seriya: Ekonomika = Herald of Omsk University. Series Economics, 2020, vol. 18, no. 2, pp. 65–79. URL: Link (In Russ.)
17. Granitsa Yu.V. [Selection of regional determinants of economic security]. Finansy i kredit = Finance and Credit, 2022, vol. 28, iss. 12, pp. 2825–2851. (In Russ.) URL: Link
18. Kononova N.V., Mangalova E.S., Stroev A.V. et al. Applied classification problems using ridge regression. Sibirskii zhurnal nauki i tekhnologii = Siberian Journal of Science and Technology, 2019, vol. 20, no. 2, pp. 153–159. URL: Link
19. Lebedev I.S. [Adaptive application of machine learning models on separate segments of a data sample in regression and classification problems]. Informatsionno-upravlyayushchie sistemy = Information and Control Systems, 2022, no. 3, pp. 20–30. URL: Link (In Russ.)
20. Koval'nogov V.N., Sherkunov V.V., Khussein Mokhamed Khusseĭn, Klyachkin V.N. [A comparative analysis of methods for constructing mathematical models of object functioning using machine learning]. Programmnye produkty i sistemy = Software & Systems, 2023, vol. 36, no. 2, pp. 189–195. URL: Link (In Russ.)

View all articles of issue

ISSN 2311-8768 (Online)
ISSN 2073-4484 (Print)

Journal current issue

Vol. 17, Iss. 1 March 2024

Archive