Exploring subjective well-being using machine learning: GDP, health, social support, and emotional factors

This study investigates the determinants of subjective well-being, emphasizing the interplay between gross domestic product (GDP), health, social support, and emotions. It aims to uncover the complex, non-linear relationships among these factors using advanced machine learning techniques applied to comprehensive global data. These models were compared with traditional linear regression approaches to evaluate their effectiveness in capturing intricate and interactive patterns. Factor analysis was also conducted to assess the relative influence of each determinant. The findings reveal that while GDP and health are significant contributors to subjective well-being, emotional and social factors – such as happiness, life satisfaction, and stress – play an equally, if not more, critical role. Machine learning models outperformed linear models by effectively capturing complex interactions that conventional methods often overlook. Moreover, factor analysis indicated that non-economic variables frequently exert greater influence than financial indicators like GDP. The study highlights the need for integrated public health strategies that combine economic policy with efforts to strengthen emotional and social well-being. These insights offer valuable implications for policy, public health, and business, advocating for a holistic approach to improving quality of life.