Optimizing Energy Consumption Efficiency in Global Industrial Systems Using the Random Forest Algorithm

This study employs the Random Forest method, a type of machine learning, to investigate strategies for improving industrial energy use. The algorithm accurately estimated energy consumption efficiency in this industry, with results indicating (MSE: 0.001, MAPE: 0.049, R2: 96.4). The findings highlight that industrial value added significantly impacts energy consumption efficiency, representing 60.2%, while industrial CO2 emissions account for 39.8%. The study uncovered a significant negative correlation between Energy consumption efficiency in the industrial sector and all industrial value added, including industrial CO2 emissions. Energy consumption efficiency in the industrial sector diminishes as industrial growth accelerates, resulting in higher emissions. Economic growth frequently leads to increased energy consumption and environmental damage. The conclusion is that the industrial sector does not use energy efficiently; the expansion of this sector will lead to inefficiency in energy use on the one hand and, on the other, an increase in emissions, which negatively affects energy use efficiency.