A Comparison of ARIMA, Neural Network and Linear Regression Models for the Prediction of Infant Mortality Rate

The aim of this paper is to compare the performances of ARIMA, Neural Network and Linear Regression models for the prediction of Infant Mortality Rate. The performance comparison is based on the Infant Mortality Rate data collected in Indonesia during the years 1995 – 2008. We compare the models using performance measures such as Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The results show that the Neural Network model with 6 input neurons, 10 hidden layer neurons and using hyperbolic tangent activation functions for the hidden and output layers is the best among the different models considered.