Forecasting Total Fertility Rate (TFR) in Eritrea Using a Machine Learning Technique

In this research article, the ANN approach was applied to analyze TFR in Eritrea. The employed annual data covers the period 1960-2018 and the out-of-sample period ranges over the period 2019-2030. The residuals and forecast evaluation criteria (Error, MSE and MAE) of the applied model indicate that the model is stable in forecasting TFR in Eritrea. The results of the study shows that annual total fertility rates in Eritrea are likely to decline slightly over the out-of-sample period. Therefore, the government of Eritrea is encouraged to (1) focus on improving access to family planning services by creating more demand for the service and addressing barriers to access, and (2) engage on a women empowerment drive to improve their labor participation and contribution to economic development.