Revealing the Complexities of Holistic Happiness: A Multi Data-Source Analysis of Key Factors

The World Happiness Report (WHR), released every year by Gallup includes measures of overall well-being and satisfaction among the global population. Using machine learning techniques like support vector machines (SVM), decision trees, and linear regression, the goal of this study is to uncover the complexity of holistic happiness. The dataset used included the World Happiness Report by Gallup and the World Income Inequality Database (WIID). Two sets of machine learning models, A and B, were developed. Models set A is based on the traditional predictors, which use metrics like GDP per capita, life expectancy, generosity, perceptions of corruption, freedom to choose, and social support to forecast happiness. Model set B includes an additional attribute (income inequality) from WIID. The outcome of the study showed that the inclusion of income inequality help improves the model performance and helps to better understand the patterns of happiness across different income levels and how income inequality affects overall happiness. It could have a significant impact on future research and our ability to predict happiness index across countries. Through rigorous analysis, the research yielded a notable R-squared value of 0.79, indicating a strong correlation between the identified factors and happiness.