Toward <scp>SDG</scp> 13: A Machine Learning‐Based Assessment of Financial Freedom, Investment Freedom, and Environmental Sustainability

ABSTRACT Previous studies in the context of the finance‐environment nexus mainly rely on quantitative indicators to provide information on activity or depth of the financial system, ignoring how institutional openness and the degree of regulatory autonomy within the financial market shape environmental outcomes that are directly relevant to Sustainable Development Goal (SDG) 13. Accordingly, in line with the objectives of SDG 13, this research provides the first assessment of the nonlinear impacts of financial freedom (FFRE) and investment freedom (IFRE) on the ecological footprint (EF), a comprehensive indicator of environmental pressure. The Kernel‐Based Regularized Least Squares (KRLS) machine learning approach is applied to analyze the G7 data (2000–2024), and the Feasible Generalized Least Squares (FGLS) is utilized for robustness. The novel findings reveal positive average marginal effects of FFRE on EF, indicating that a more liberalized financial system poses greater environmental pressure. However, the analysis at various levels of FFRE reveals non‐linearities, disclosing that the positive effects of FFRE on EF reverse at a higher level. Thus, FFRE reduces EF at higher levels of FFRE. IFRE poses negative marginal impacts on EF on average, indicating that higher investment freedom promotes environmental sustainability; however, the magnitude of those negative effects weakens at higher levels of IFRE. The analysis reveals a positive marginal effect of industrialization (IND), economic growth (EG), and population growth (PGR), indicating that these forces enhance EF. Conversely, the renewable energy transition (RET) curbs EF, promoting environmental sustainability. Based on the results, detailed policy directions are discussed.