Money talks, happiness walks: dissecting the secrets of global bliss with machine learning

Abstract

ABSTRACT This study endeavors to construct a model for prognosticating happiness by integrating an encompassing theoretical framework and scrutinizing various happiness constructs. The findings reveal that the Random Forest outperforms its counterparts, exhibiting an astounding accuracy rate of 92.2709. Furthermore, the results uncover a conspicuous and pronounced divergence between joyful and despondent nations concerning their GDP per capita. The former exhibits a remarkable ascendency in this economic indicator relative to their less contented counterparts. The research posits far-reaching policy, managerial, and social implications. It underscores its significance in steering the realization of the United Nations’ Sustainable Development Goals (SDGs), including Goals 3, 4, 8, and 10. The study recommends that SDG-driven efforts should be bolstered to hasten the attainment of happiness in developing countries while promoting the adoption of data-driven decision-making approaches in policy formulation and the development of efficacious policies.