Tracking the Future Path of Under Five Mortality in Zambia Using the Multilayer Perceptron Neural Network

This study uses annual time series data on under five mortality rate (U5MR) for Zambia from 1960 to 2020 to predict future trends of U5MR over the period 2021 to 2030. Residuals and forecast evaluation criteria indicate that the applied ANN (12, 12, 1) model is stable in forecasting under five mortality rate. ANN model forecast results indicated thatU5MR will remain high over the out of sample period. Therefore, we encourage the Zambian government to allocate more resources to the maternal and child health (MNCH) program and address all the factors that significantly contribute to under five mortality across the country.