Life Expectancy Prediction using Recursive Partitioning and Bagging Algorithms

Life expectancy is a crucial indicator of the population’s health and well-being. Recent research has highlighted the importance of various socioeconomic and health factors in determining the lifespan of individuals. Those factors include Gross Domestic Product (GDP), healthcare expenditure, mortality rates, and education level. This study employs recursive partitioning (decision trees) and bagging (random forest) techniques on the Life Expectancy dataset from the World Health Organization (WHO) to evaluate the effectiveness of predictive models. The dataset was prepared by encoding categorical features, scaling the features, normalizing them, and handling outliers. Mean imputation was used to handle missing values and produce a quality dataset. Optimized models based on recursive partitioning and bagging algorithms achieved performance efficiencies of 92% and 97%, respectively. The bagging algorithm-based model produced a mean squared error of 1.17, a mean absolute error of 2.0, and an R2-score of 97%. Other key findings included the importance of dataset characteristics—such as HIV/AIDS prevalence, adult mortality, and health resource income—in predicting life expectancy. This research elucidates the impact of feature engineering and data preprocessing strategies on data quality and predictive model precision, offering novel insights for public health policymaking and informing future research directions.