Predictive Modeling of Life Expectancy Using Machine Learning Algorithms

Life expectancy, a pivotal public health measure, indicates the average lifespan based on current mortality rates and reflects societal well-being. Over the last century, it has significantly increased due to medical advancements, improved living standards, and public health initiatives. Factors like healthcare quality, lifestyle, social status, and environment have profound influence on this improvement in Life Expectancy. However, disparities persist due to uneven access to healthcare, education, and jobs. This study deploys various machine learning models, to predict life expectancy, achieving an adjusted R-squared value of 0.9729 by Extra Tree Regression, indicating exceptional model accuracy. By analyzing a comprehensive dataset, socio-economic, health, and environmental factors such as GDP per capita, composition of resources, education levels etc., were identified as key predictors of life expectancy by the model. The high R-squared value highlights the model's robustness in capturing dynamic relationships between these variables and life expectancy.