Smart Investment Strategies in Sustainable Energy via Machine Learning

The global transition to clean energy is essential for addressing the urgent challenges posed by climate change, enhancing energy security, and promoting sustainable economic growth. In this context, machine learning (ML) offers powerful capabilities to forecast trends in sustainable energy markets, evaluate the feasibility of renewable energy projects, and optimize financial strategies to balance economic viability with environmental responsibility. This study explores the effectiveness of various machine learning algorithms in predicting investments in clean energy. Through comprehensive data preprocessing-including outlier detection, feature selection, and normalization-the quality of input data was significantly enhanced, leading to improved model performance. A range of ML models were evaluated, including Linear Regression, Artificial Neural Networks, Random Forests, and XGBoost. Performance was assessed using metrics such as <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{\mathbf{2}}$</tex>, Adjusted <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{2}$</tex>, Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Among the models tested, the Random Forest algorithm demonstrated superior predictive performance, achieving an <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R}^{\mathbf{2}}$</tex> score of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 9. 1 0 \%}$</tex> on the training set and 73.60% on the validation set. It also yielded the lowest RMSE values, highlighting its accuracy and reliability. These findings emphasize the transformative potential of machine learning in guiding investment strategies and supporting data-driven decision-making in the sustainable energy sector.