Data-driven linking of national well-being to sustainable development: A machine learning and multi-phase analysis framework

• Links national well-being to SDG progress using a three-phase analytical framework. • Integrates machine learning and MCDM to assess resilience and sustainability patterns. • Proposes a happiness-based resilience metric to evaluate post-crisis national recovery. • Predicts SDG outcomes using well-being indicators through robust ML regression models. National happiness provides a comprehensive measure of societal well-being, transcending traditional economic indicators such as Gross Domestic Product (GDP) by including mental health, social cohesion, and environmental sustainability. However, research frequently neglects how happiness, Sustainable Development Goals (SDGs), and resilience are interconnected, particularly during global crises. This study directly addresses these gaps, introducing a spatial and temporal framework—integrated with machine learning and a three-phase analysis—that explicitly connects national happiness with SDG progress and resilience to global shocks. Using Multi-Criteria Decision Making (MCDM), countries are evaluated on happiness scores from key indicators, offering nuanced regional and temporal insights into well-being. The results demonstrate clear patterns between national happiness and SDG alignment, especially in crisis periods like COVID-19. Notably, even countries with high happiness may face vulnerability to severe shocks, highlighting the necessity for balanced strategies that support both well-being and resilience. Policymakers are provided with actionable insights to strengthen national stability and sustainable development, positioning happiness as a dynamic, strategic indicator of progress toward SDGs and resilience.