The interrelation among environmental quality, public accounts, and macroeconomic fundamentals: An analysis of OECD countries using machine learning techniques

This study explores the intricate relationships among environmental quality, public finance indicators, and socioeconomic variables in OECD countries, using Machine Learning (ML) techniques for the period 1990–2021. The research uniquely identifies key factors influencing renewable energy consumption (REC) by incorporating various public finance indices, macroeconomic fundamentals, trade measures, and socio-economic variables. By emphasizing the role of public debt policies, the study uncovers their significant yet complex and non-linear influence on renewable energy adoption. Unlike existing studies, this research utilizes Neural Networks (NN), a state-of-the-art ML technique, to generate robust and reliable outcomes. This methodological innovation sets the study apart by offering more accurate feature importance scores compared to traditional econometric methods. The findings advance our understanding of the crucial role that public finance plays in achieving Sustainable Development Goals (SDGs), particularly SDG-7, and underscore the necessity of effective public debt management for fostering environmental sustainability. Policy implications drawn from the results provide actionable recommendations for governments to enhance REC adoption while achieving broader environmental goals. • Public debt significantly influences renewable energy adoption in OECD countries. • Neural Networks outperform other ML techniques in analyzing renewable energy data. • GDP, inflation, unemployment, government revenue, and expenditure explain renewable energy consumption. • Efficient public debt management is crucial for achieving Sustainable Development Goals.