Exploring Socioeconomic Influences on Life Expectancy through Machine Learning Ensemble Regression Techniques

Life expectancy prediction is a critical area in public health research, aiding in policy formulation and resource allocation. In this study, we explored the prediction of life expectancy using a dataset sourced from Kaggle. Initially, the dataset underwent rigorous preprocessing to handle missing values and ensure data quality. Subsequently, a diverse array of regression models, including Multiple Linear Regression (MLR), SVM, Gradient Boosting, Random Forest, XGBoost, and Decision Tree were applied to the dataset. Through thorough evaluation, the top-performing models were identified, and a comparative analysis was conducted. Leveraging ensemble learning techniques, specifically stacking and voting ensemble, further refinement was achieved, resulting in a robust predictive model with high R-squared values. The results highlight the effectiveness of ensemble regression methods in forecasting life expectancy, offering valuable insights for public health policy and decision-making.