Prediction of Spatial Effects and Factors of Regional Development Using Machine Learning Methods
( Pp. 23-30)

When modeling the spatial development of a territory, taking into account spatial effects, it is important to keep in mind that the current development of the territory is influenced not only by internal indicators (economic, social, demographic, infrastructural, etc.), but also by the processes taking place in neighboring areas. When modeling the spatial development of the Russian Federation, it is necessary to take into account spatial heterogeneity, long distances, transport corridors and climatic conditions. Accounting for these complex components includes modeling of inter-regional and intra-regional interaction. The aim of the study is to assess the impact of socio-economic factors on the gross regional product (GRP), taking into account the spatial relationship between the federal districts and time dynamics. To achieve the goal, the following tasks were solved in the work: 1) a comprehensive analysis of approaches to modeling the spatial development of regions has been carried out; 2) an adapted methodology of spatial analysis has been developed, including: a comprehensive system of indicators of socio-economic development that takes into account the specifics of Siberian regions, a typology of spatial econometric models. Materials and methods. The econometric spatial modeling apparatus was used in the modeling. Conclusions. Spatial econometric models provide a more accurate description of socio-economic processes in federal districts compared to traditional approaches that do not take into account the spatial structure of data.

Mikhailova S.S., Grineva N.V., Korablev Yu.A., and Bachaev U.A. Prediction of spatial effects and factors of regional development using machine learning methods. Computational Nanotechnology. 12, 3 (2025), 23–30. DOI: 10.33693/2313-223X-2025-12-3-23-30. EDN: AORZVF

Baltagi B.H. Econometric analysis of panel data. 3rd ed. Chichester: John Wiley & Sons, 2005. 401 p. ISBN: 978-0470844940.
Wooldridge J.M. Econometric analysis of cross section and panel data. 2nd ed. Cambridge, MA: MIT Press, 2010. 1064 p. ISBN: 978-0262232586.
Elhorst J.P. Specification and estimation of spatial panel data models. International Regional Science Review. 2003. Vol. 26. No. 3. Pp. 244–268.
Elhorst J.P. Spatial panel data models. In: Handbook of applied spatial analysis. Berlin; Heidelberg: Springer, 2010. Pp. 377–407.
Lee L.F., Yu J. QML estimation of spatial dynamic panel data models with time varying spatial weights matrices. Spatial Economic Analysis. 2012. Vol. 7. No. 1. Pp. 31–74.
Lee L.F., Yu J. Spatial panels: Random components versus fixed effects. International Economic Review. 2012. Vol. 53. No. 4. Pp. 1361–1387.
Kuersteiner G.M., Prucha I.R. Dynamic spatial panel models: networks, common shocks, and sequential exogeneity. Econometrica. 2020. Vol. 88. No. 5. Pp. 2109–2146.
Gao Z., Ma Y., Wang H., Yao Q. Banded spatio-temporal autoregressions. arXiv preprint. 2018. arXiv:1812.09264.
Yan Y., Huang H.-C., Genton M. G. Vector autoregressive models with spatially structured coefficients for time series on a spatial grid. arXiv preprint. 2020. arXiv:2001.00565.
Glass A., Kenjegalieva K., Sickles R.C. A spatial autoregressive stochastic frontier model for panel data with asymmetric efficiency spillovers. Journal of Econometrics. 2015. Vol. 190. No. 2. Pp. 289–300.

spatial development, autocorrelation, panel data, forecasting, socio-economic factors, machine learning.