What is the impact of socioeconomic and sociodemographic factors on Life Satisfaction

This study explores the impact of socioeconomic and sociodemographic factors on Life Satisfaction. As discussions about mental health have increased over the years, researchers have since tried to unveil the key indicators of subjective well-being through data science techniques. In this context, authors have emphasized the importance of incorporating supervised and unsupervised approaches in the studies of Life Satisfaction. This dissertation delivers a combined integration of explanatory and predictive analysis on a large dataset of socioeconomic and sociodemographic indicators. The explanatory significance of the variables is assessed and compared through Ordinary Least Squares (OLS) regression modelling – latent factors vs. the original variables – while the predictive accuracy of the predictors is evaluated through Machine Learning algorithms such as Random Forest, AdaBoost Regressor and Multi-Layer Perceptron Regressor. The performance of these models is then evaluated via error metrics like the Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and R-squared. By providing valuable insights, this study supports stakeholders in policy and decision- making processes.