Econometric model of energy: Russia’s response to the challenges of the global economy

The relevance of the study is due to both the high degree of importance of energy for the economic development of Russia and the insufficient use of econometric models in modern energy research. The purpose of the study is to develop and propose an econometric model of the country’s fuel and energy resources. In line with this objective, the research provides a detailed examination of the methodological framework and key stages involved in developing an econometric model using autoregressive analysis for the purpose of studying the Russian energy sector. This is both the scientific and applied, as well as the scientific and methodological significance of the presented publication. To achieve this goal, statistical materials from Rostat “Consumption of fuel and energy resources per person employed in the country’s economy” have been used since 2012. Econometric analysis and statistics are used as a methodology, in particular, an autoregressive analysis model is used. The methodological advantage of the autoregressive model is its flexibility when working with a wide range of different time series patterns. Data Science methods were used to develop the model in particular, cMLE (conditional maximum likelihood method). The autoregressive model itself is written in the high-level Python language. Pandas, Numpy, Statsmodels, Sklearn.metrics, and Matplotlib libraries and modules were used. The study describes in detail the main stages of building an autoregressive model: data selection, visualization and verification for stationarity, data separation into test and training samples, training of an autoregressive model, RMSE analysis. The data obtained are characterized by the absence of an obvious trend: there have been periods of a decrease in the consumption of fuel and energy resources per person employed in the country’s economy since 2012, as well as periods of an increase in the corresponding consumption in tons of conventional fuel. The study concludes that the autoregressive model is applicable to the analysis of the Russian energy sector. Although the time series of data is limited, the autoregressive model has high predictive characteristics. The “conservatism” of the autoregressive model towards underestimating the forecast values is emphasized. It is indicated that as new energy statistics accumulate, the autoregressive qualities of the model will improve.