Predicting Child Mortality With Diverse Regression Algorithms Using a Machine Learning Approach

Abstract

This chapter uses machine learning methodologies to investigate the prediction of child mortality rates for ages 1-4 across diverse countries. Drawing upon a comprehensive review of global health data from organizations such as the World Health Organization (WHO) and the United Nations Children's Fund (UNICEF), which highlight the urgency and significance of accurate child mortality prediction, the authors analyze a dataset spanning from 1967 to 2019, containing 30,940 entries from countries worldwide. Regression algorithms, including XGBoost, CatBoost, Random Forest, AdaBoost, and DecisionTree Regressor, are employed to predict child mortality rates. Evaluation metrics such as R^2, adjusted R^2, mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE) are utilized to assess model performance. Additionally, Matplotlib and Seaborn use visualization techniques to illustrate the findings through pie charts and graphs. The analysis aims to identify the most effective algorithm for accurately forecasting child mortality rates, thereby contributing to advancing healthcare planning and intervention strategies to reduce child mortality globally.