Territorial Planning and Forecasting of Economic Indicators by Machine Learning Methods

Yury A. Pleskachyev – Senior Researcher of the Russian Presidential Academy of National Economy and Public Administration (Moscow, Russia). E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Yury Yu. Ponomarev – Head of Laboratory for Infrastructure and Spatial Research of the Russian Presidential Academy of National Economy and Public Administration, Candidate of Economic Sciences (Moscow, Russia). E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Matvey A. Saprykin – Junior Researcher of the Russian Presidential Academy of National Economy and Public Administration (Moscow, Russia). Е-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Forehanded consideration of economic development forecasts for both macroeconomic and microeconomic situation in the region and the metropolis is an important element in territorial planning and urban development in modern conditions. The article proposes an approach to forecasting economic indicators, which would allow simultaneously taking into account the dynamics of macroeconomic factors and the effects of individual program and strategic documents implementation (using the measures of national projects as an example). Using several options of modern model architectures, we show the most effective model in terms of forecast accuracy based on their approbation on two important indicators for the sphere of territorial planning – investments in fixed assets and real disposable incomes of the population.

The article was prepared as part of the research work of the state task of the RANEPA.

Key words: forecasting, planning, machine learning.

JEL-codes: C40, C45, R53, E22, D31.