Applying Machine Learning Techniques to Predict Child Death Rates

Child mortality refers to the death of children under the age of five, including deaths that occur during infancy and even in the womb. The under-five mortality rate indicates the likelihood of death between birth and five years of age. This study focuses on analyzing AI-based techniques for the classification of child health status, aiming to improve prediction accuracy. The dataset is examined using supervised machine learning techniques (SMLT) to uncover insights such as variable identification, univariate, bivariate, and multivariate analyses, handling of missing values, data validation, cleaning/preprocessing, and visualization. Our research presents a comprehensive guide to sensitivity analysis of model parameters and their impact on classification performance. The goal is to propose an AI-based solution and compare the performance of various machine learning algorithms on the given dataset.