Forecasting Total Fertility Rate (TFR) In Sri Lanka Using a Machine Learning Algorithm

In this research paper, the ANN approach was applied to analyze TFR in Sri Lanka. 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 Sri Lanka. The results of the study indicate that annual total fertility rates in Sri Lanka are likely to remain around 2.3 births per woman over the out-of-sample period. Therefore, the authorities in Sri Lanka are encouraged to continue improving accessibility of family planning services to adolescents and young adults to minimize adverse SRH outcomes.