Revealing Renewable Energy Barrier in LMICs: A Machine Learning and Econometric Approach for Policymaking

Abstract This study analyzes factors influencing renewable energy development (RE) in low- and middle-income countries (LMICs) using machine learning-econometric approach combing Random Forest (RFM) and Fixed Effects Modeling (FEM). Findings revealed financial access (DCPS) facilitates RE adoption, while high interest rates (INR_Log) hinder it. Corruption control (CC) and government effectiveness (GE) are crucial. Foreign investment (FDI_Log) has significant asymmetric impacts on clean energy goals. Energy imports (EIMP) vary in importance by context. This research links energy transitions, economic growth, and institutional quality key aspects of SDGs 7 and 8. It recommends financial reforms, anti-corruption measures, and interest rate adjustments to develop inclusive, resilient energy systems. The machine learning–econometric approach offers policymakers a strong framework for evidence-based strategies. Future research should integrate sector-specific variables, industrial RE adaptation, and use XGBoost or SHAP with a larger dataset, particularly from Asia and the Middle East. JEL: C01, C23, O13, O44, Q01, Q42, Q54