Determinants of Uneven Progress in Sustainable Development in the EU: Predictive Approaches Based on Machine Learning
Determinants of Uneven Progress in Sustainable Development in the EU: Predictive Approaches Based on Machine Learning

Summary/Abstract: This paper investigates the relative importance of distributional versus structural socioeconomic variables in predicting the performance of Sustainable Development Goals (SDG) across European Union member states. Using a comprehensive panel dataset and advanced machine learning techniques, the study demonstrates that distributional indicators such as income inequality and poverty thresholds have stronger and more consistent predictive power than traditional macroeconomic measures. Moreover, the research uncovers a non-linear relationship between inequality and SDG outcomes, revealing a threshold effect where reductions from high to moderate inequality levels yield greater improvements than further reductions. Finally, regional location within Europe is found to be a significant predictor of SDG performance even after controlling for economic and social factors, highlighting persistent structural differences between Southern and Northern/Western European regions. These findings offer robust insights for policymakers aiming to design more targeted and equitable sustainability strategies.

• Details
• Contents