Forecasting the Gross Domestic Product of the Philippines using Bayesian artificial neural network and autoregressive integrated moving average

The researcher aim to forecast the Gross Domestic Product (GDP) of the Philippines from the 1st Quarter of 2018 to 4th Quarter of 2022. Furthermore, this study determines the most suitable model among Autoregressive Integrated Moving Average and Bayesian Artificial Neural Network that can forecast the GDP of the Philippines. The researcher used the data ranging from the 1st Quarter of 1990 up to 4th Quarter of 2017 with a total of 112 observations. Statistical test are conducted within the study to be able to formulate and compare the statistical model ARIMA and Bayesian ANN. It is concluded in this study that the ARIMA(1,1,1) and Bayesian ANN can forecast the GDP of the Philippines. The researcher use Forecasting accuracy such as MSE, NMSE, MAE, RMSE, and MAPE to compare the performance of two models. In this paper, the best fitted model obtained is Bayesian ANN. Paired T-test concludes that there is no significant difference between actual and predicted value. This study helps economics specifically in economic forecasting and economic analysis.