Machine Learning-Based Life Expectancy Prediction in Developed and Developing Regions

The project focuses on predicting life expectancy across developed and developing regions using machine learning techniques. Accurate life expectancy prediction can provide insights into public health, socio-economic conditions, and resource allocation. The dataset utilized contains features such as country, year, health indicators, socio-economic factors, and demographic statistics. Several regression algorithms, including Linear Regression, Random Forest, XGBoost, Gradient Boosting, Stacking Regressor, and Voting Regressor, are implemented to model and predict life expectancy. The performance of each algorithm is evaluated using suitable metrics to determine accuracy and reliability. Additionally, a Flask-based web interface is developed, enabling users to input data and obtain predictions efficiently. This framework can assist researchers and analysts in understanding health trends across regions. The study demonstrates the potential of machine learning in analyzing large datasets and deriving meaningful insights for life expectancy prediction.

Keywords: life expectancy, prediction, machine learning, linear regression, random forest, XGBoost, gradient boosting, stacking regressor, voting regressor, health analytics