FORECASTING THE GRP OF THE URAL MACROREGION REGIONS USING LSTM MODELS IN THE CONTEXT OF ECONOMIC RESTRUCTURING

EDN: JSVGED

DOI: https://doi.org/10.65891/2949-1983-2026-22-2-10-13

Authors:

KUKLINOVA Polina Sergeevna

Affiliation:

Ural State University of Economics

Abstract.

The current economic situation is characterized by high uncertainty: sanctions restrictions, import substitution policies, and industrial restructuring require more accurate and adaptive forecasting tools from regional authorities. For the subjects of the Ural macro-region, where the industrial sector remains systemically important, such tools are of particular importance. The article proposes a neural network model for forecasting gross regional product (GRP) based on recurrent networks with long-term short-term memory (LSTM). The initial data are the official statistics of Rosstat for 2005–2024 for six regions of the macroregion. To improve the accuracy of forecasts, preliminary clustering of territories with a similar industry structure was applied, which made it possible to expand the training samples at the expense of analog regions. A comparative assessment showed that the LSTM model reduces the root-mean-square error by 18–25 % for industrial regions and by 12–15 % for resource regions compared to the classical ARIMA. The developed approach can be used by regional governments to clarify budget parameters and adjust development strategies.

Keywords:

Gross regional product (GRP), neural network modeling, LSTM networks, forecasting, Ural macroregion, regional economy

References:

1. Samsonov, A.V. Forecasting the dynamics of regional GRP using recurrent neural networks / A.V. Samsonov, L. I. Sergeev // Russian Economic Bulletin. – 2021. – Vol. 4, No. 5. – pp. 240-252. – EDN ETSFAV.
2. Kulova M. R., Sokolova E. B., Fedosova E. V. Comparative analysis of statistical and neural network methods of forecasting GRP (on the example of North Ossetia-Alania) // Financial business. – 2025. – № 11(269). – Pp. 52-56. – EDN RNFHUC.
3. Azarnova T. V., Treshchevsky Yu. I., Papin S. N. Forecasting the parameters of socio-economic development of a region using neural network apparatus (using the example of GRP in the Voronezh region) // Modern economics: problems and solutions. – 2020. – № 3(123). – Pp. 8-25. – DOI 10.17308/meps.2020.3/2321. – EDN PKXNNJ.
4. Yelshin L. A., Gatin A.D., Mingulov A.M. Methodological approaches to the prognostic assessment of the dynamics of GRP in the region in the context of sanctions attacks // Modern management technologies. – 2024. – № 1(105). – EDN CZAFPS.
5. Ghazo, A. Applying the ARIMA Model to the Process of Forecasting GDP and CPI in the Jordanian Economy / A. Ghazo // International Journal of Financial Research. – 2021. – Vol. 12, No. 3. – P. 70. – DOI 10.5430/ijfr.v12n3p70. – EDN SGMFME.
6. Barbaglia, L. Forecasting GDP in Europe with textual data / L. Barbaglia, S. Consoli, S. Manzan // Journal of Applied Econometrics. – 2024. – Vol. 39, No. 2. – P. 338-355. – DOI 10.1002/jae.3027. – EDN WYINXX.
7. Chow, H. K. Forecasting GDP with many predictors in a small open economy: forecast or information pooling? / H. K. Chow, Y. Fei, D. Han // Empirical Economics. – 2023. – Vol. 65, No. 2. – P. 805-829. – DOI 10.1007/s00181-022-02356-9. – EDN RRTOTG.
8. Yusuf, M. A. Forecasting GDP Per Capita in the USA: Integrating Econometric and Machine Learning Approaches for Policy Insights / M. A. Yusuf // International Journal of Innovative Science and Research Technology (IJISRT). – 2025. – P. 2081-2100. – DOI 10.38124/ijisrt/25mar1083. – EDN FBMQJY.
9. Galimberti, J. K. Forecasting GDP Growth from Outer Space / J. K. Galimberti // Oxford Bulletin of Economics and Statistics. – 2020. – Vol. 82, No. 4. – P. 697-722. – DOI 10.1111/obes.12361. – EDN EVVFUK.
10. Kitrar, L. A. Forecasting GDP growth taking into account crisis shocks based on the results of business activity surveys / L. A. Kitrar, T. M. Lipkind, N. A. Usov // Questions of statistics. - 2021. – Vol. 28, No. 4. – pp. 80-95. – DOI 10.34023/2313-6383-2021-28-4-80-95. – EDN TXOJFG.
11. Aralbayeva, G. G. Analysis of the structure and dynamics of GRP of the Kyzylorda region of the Republic of Kazakhstan / G. G. Aralbayeva, U. D. Berikbolova // Economics and Entrepreneurship. – 2023. – No. 7(156). – P. 462-467. – DOI 10.34925/EIP.2023.156.7.077. – EDN PFXYYZ
12. Kholodnaya, A. K. Peculiarities of the influence of interregional imbalances in the share of research staff on GRP per capita / A. K. Kholodnaya // Bulletin of Vladimir State University named after Alexander Grigoryevich and Nikolai Grigoryevich Stoletov. Series: Economic Sciences. – 2020. – № 2(24). – Pp. 5-8. – EDN TRSNDH.
13. Smirnova, O. P. The influence of digital technologies of industries on the economic growth of industrial regions / O. P. Smirnova, L. K. Chesnyukova // Regional economics: theory and practice. – 2023. – Vol. 21, No. 9(516). – pp. 1653-1670. – DOI 10.24891/re.21.9.1653. – EDN LOVNAT.
14. Smirnova, O. P. Technological transformation of industry as a factor of economic growth: statistical analysis for the period 2010-2022 / O. P. Smirnova, L. K. Chesnyukova // Financial analytics: problems and solutions. – 2024. – Vol. 17, No. 1(367). – pp. 56-73. – DOI 10.24891/fa.17.1.56. – EDN AJRLMJ.
15. Rotkevich, T. A. Forecasting the dynamics of electricity consumption and electrical consumption of GRP as an element of the program of regional socio-economic development / T. A. Rotkevich // Fundamental and applied research of the cooperative sector of the economy. – 2025. – No. 4. – pp. 125-133. – EDN VABOTI.
16. Smirnova, O. Assessment of Sustainable Development Potential and the Green Growth of the Russian Macro-Region / O. Smirnova, L. Chesnyukova // Green Taxonomy for Sustainable Development: From Green Technologies to Green Economy, Tashkent, Uzbekistan, June 14-16, 2024. Vol. 574. – EDP Sciences - Web of Conferences, Les Ulis, France: EDP Sciences - Web of Conferences, 2024. – P. 02004. – DOI 10.1051/e3sconf/202457402004. – EDN MBBMPQ
17. Kumar, V. Technological development of smart industrial regions in Russia: A cluster analysis / V. Kumar, O. Smirnova, L. Chesnyukova // E3S Web of Conferences : VII International Scientific Conference “Cities of New Age: GLASS" (REC-2023), Yekaterinburg, June 27-29, 2023. Vol. 435. – Ekaterinburg: EDP Sciences, 2023. – P. 03001. – DOI 10.1051/e3sconf/202343503001. – EDN XQEOLC.
18. Filatov, D. V. Clusterization of Russian regions by the structure of household income / D. V. Filatov, L. K. Chesnyukova, N. S. Pankin // Horizons of Economics. – 2025. – № 5(92). – Pp. 32-41. – EDN GJNTLG.
19. Tsekhan, O. B. Analysis of the GRP of China's provinces based on multiple regression models / O. B. Tsekhan, Ya. Zhu // Vesnik of Yanka Kupala State University of Grodno. Series 5. Economics. Sociology. Biology. – 2021. – Vol. 11, No. 3. – P. 64-72. – EDN VFIRIL.
20. Aralbaeva, G. G. Statistical studies of the impact of innovations, investments in innovations and exports on the GRP of the Kyzylorda region of the Republic of Kazakhstan / G. G. Aralbaeva, U. D. Berikbolova // International Research Journal. – 2021. – No. 9-2(111). – P. 138-142. – DOI 10.23670/IRJ.2021.9.111.060. – EDN PVFPQJ.