Child mortality rate is a leading indicator for health in children and by extension a measure of the country’s health system. Child mortality, or the under-five mortality rate, can be defined as the rate of a child dying between birth and exactly 5 years of age, expressed per 1000 live births. Every year, millions of children age below 5 years old die globally. Fortunately, some of these deaths can be prevented. Reducing the mortality rate of these age groups is one the targets among the 17 Sustainable Development Goals by the United Nations. Thus, the purpose of this study is to develop a model that can predict under-five mortality rate based on other socioeconomic indicators.
Linear regression with Lasso variable selections and decision trees are carried out to compare the performance of these models to predict the under-5 mortality rate.