Using Machine Learning Methods for Analyzing and Forecasting of Small Samples of Macroeconomic Indicators in the Energy Sector of the Russian Federation

Forecasting methodologies are widely applied in the analysis of socio-economic systems. Employing robust forecasting techniques enables organizations to anticipate future developments, optimize resource allocation, and mitigate potential risks. In the energy sector, accurate forecasting of supply and demand is essential for maintaining grid stability, reducing operational costs, and enhancing reliability. This study aims to assess the effectiveness of statistical and neural network modeling methods in forecasting macroeconomic indicators within the energy sector of the Russian Federation.