Social Development Forecast for Russian Regions

The objective of the article is to offer a proprietary technology for assessment and forecasting of social development of Russian regions. The methodological basis of the study is neural network technology (a Bayesian ensemble of dynamic neural networks of different configurations is formed) that ensure high accuracy of the forecast. The authors developed a methodology for assessing the social potential of the Russian regions. They have also designed a system of private indicators characterising the level of social development of Russian regions. The indicators have been divided into five groups: 1) population (life expectancy); 2) standard of living of the population; 3) education; 4) health care (morbidity); 5) research and innovation. The private indicators have been made comparable by normalizing their values by means of “Pattern” method. This method allows the objective assessment of the interregional “gaps” in the country across the entire system of social indicators. The social development index of the subjects of the Russian Federation has been calculated. Based on neural network technologies (Kohonen self-organizing maps) clustering of regions of Russia regarding social development has been conducted. The forecast of the social development of the Russian regions has been made. Due to the forecast, it has been established that in the leading region of the Russian Federation (Moscow) in 2017-2019 the decrease is expected in the index of social development in comparison with 2014-2016. In another leading region of the Russian Federation (St. Petersburg) the decline in comparison with 2016 is expected in the medium term. At the same time, for the Republic of Bashkortostan in 2017-2019, just a slight decrease in the level of social development is forecasted. However, it is expected that the Republic will still lag significantly behind the leading regions of Russia by social development. The example of the Republic of Bashkortostan helped to discover that the lag in social development can be explained by the “gap” in research and innovations. The authors have concluded that it is necessary to improve the effectiveness of social policy at the regional level. Thus, it is necessary not only to increase financing of the social sphere of the subjects of the Russian Federation, but also to ensure proper control of budget spending. The developed methodology can be an effective tool for forecasting and managing social development of the Russian regions by the relevant ministries and departments.

forecasting social development of the region, assessment methodology, clustering of regions, share of budget expenditures, social financing, Kohonen self-organizing maps, a Bayesian ensemble of dynamic neural networks, multilayer perceptron

1. Dregalo A. A., Ul’yanovskii V.I., Bryzgalov V. V., Krikunenko V. I., Shekhina T. P. Social potential of the region as a factor in the development of the northern territories. Arkhangelsk: Northern State Medical Univ. Publ.; 2008. 400 p. (In Russ.).

2. Ivanov S. A., ed. Human potential for innovative economy. St. Petersburg: State Univ. of Aerospace Instrumentation; 2011. 188 p. (In Russ.).

3. Korchagin Yu. A. Russian human capital: A factor of development or degradation? Voronezh: Center for Regional Economic Studies; 2005. 252 p. (In Russ.).

4. Bourdieu P. Forms of capital. Transl. from Eng. Ekonomicheskaya sotsiologiya = Economic Sociology. 2002;3(5):60-74. (In Russ.).

5. Coleman J. Social and human capital. Transl. from Engl. Obshchestvennye nauki i sovremennost’ = Social Sciences and Contemporary World. 2001;(3):121-139. (In Russ.).

6. Putnam R. Making democracy work: Civic traditions in modern Italy. Transl. from Eng. Moscow: Ad Marginem; 1996. 288 p. (In Russ.).

7. Shafikov M. T. Scientific and educational potential of the region: Essence, structure, state and dynamics. Ufa: Gilem Publ.; 2002. 106 p. (In Russ.).

8. Podberezkin A. I. National human capital. Vol. III: Ideology of Russian socialism. Bk. 2: Ideology of Russian socialism and the strategy of national development. Moscow: Editorial URSS; 2011. 621 p. (In Russ.).

9. Lapshin V. A. Structural components of human potential. Znanie. Ponimanie. Umenie = Knowledge. Understanding. Skill. 2013;(1):259-263. (In Russ.).

10. Bokareva V. B. Social potential of the Russian small business in the conditions of globalisation. Vestnik Novosibirskogo gosudarstvennogo universiteta. Seriya: Sotsial’no-ekonomicheskie nauki = Vestnik NSU. Series: Social and Economic Sciences. 2001;11(3):196-204. (In Russ.).

11. Fayzullin F. S., Shagieva L. A. Social potential of the region as an object of sociological analysis. Vestnik VEGU. 2016;(3):118-124. (In Russ.).

12. Gagarina G. Yu., Gubarev R. V., Dzyuba E. I., Fayzullin F. S. Forecasting of socio-economic development of the Russian regions. Ekonomika regiona = Economy of Region. 2017;13(4):1080-1094. DOI: 10.17059/2017- 4-9 (In Russ.).

13. Mikhalkina E. V., Kosolapova N. A., Senkiv O. Ya. An assessment model for the Russian regions’ socio¬economic development factors impact on the human potential building. Terra Economicus. 2015;13(2):57- 72. (In Russ.).

14. Shagieva L. A. Methods of measuring trends of development of the social potential of regions. Vestnik VEGU. 2015;(6):185-192. (In Russ.).

15. Efendieva A. A., Temrokova A. Kh. Elaboration of the methodology complex analysis and assessment of the region socio-economic potential based on the scores method. Terra Economicus. 2013;11(2-2):102-106. (In Russ.).

16. Golovko V. A. Neural networks: Training, organisation and application. Moscow: IPRZhR Publ.; 2001. 256 p. (In Russ.).

17. Rissanen J. Modeling by shortest data description. Automatica. 1978;14(5):465-471. DOI: 10.1016/0005- 1098(78)90005-5

18. Beloliptsev I. I., Gorbatkov S. A., Romanov A. N., Farkhieva S. A. Modeling of management decisions in the economy in conditions of uncertainty. Moscow: Infra-M Publ.; 2015. 299 p. (In Russ.).

19. Bukaev G. I., Bublik N. D., Gorbatkov S. A., Sattarov R. F. Modernization of the tax control system based on neural network information technologies. Moscow: Nauka; 2001. 344 p. (In Russ.).