ROLE OF ENERGY USE IN THE PREDICTION OF CO2 EMISSIONS AND ECONOMIC GROWTH: GLOBAL EVIDENCE WITH MACHINE LEARNING

This study evaluates the role of energy consumption in predicting CO2 emissions and economic growth using advanced machine learning models. By analyzing data from 220 countries spanning 1990 to 2022, the research integrates Decision Tree, Random Forest, XGBoost, LightGBM, and CatBoost algorithms to uncover key predictors and their impacts. The findings indicate that electricity and fossil fuel consumption are critical predictors of CO2 emissions, while renewable energy use significantly influences economic growth. Gradient boosting models, particularly LightGBM and CatBoost, demonstrated superior predictive performance, capturing complex relationships between energy use and economic outcomes. The study concludes that balancing fossil fuel use with renewable energy adoption is essential for sustainable economic development and environmental protection. Recommendations for investors include prioritizing renewable energy projects and supporting energy efficiency initiatives. Managers are encouraged to adopt sustainable practices and invest in innovation, while government agencies should promote renewable energy policies and enforce energy efficiency standards. These insights aim to inform policy and strategic decision-making to achieve sustainable development goals.