Forecasting Future Trends of Under Five Mortality Rate for the Dominican Republic Using Artificial Neural Networks

This study uses annual time series data on under five mortality rate (U5MR) for the Dominican Republic 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 projections suggest that annual U5MR will hover around 35 deaths per 1000 live births over the out of sample period. Therefore, the Dominican Republic must allocate more resources to the maternal and child health (MNCH) program and attend to all the problems that significantly contribute to under five mortality.