FORECASTING ALGERIAN GDP USING ADAPTIVE NEURO FUZZY INFERENCE SYSTEM DURING THE PERIOD 1990-2019

Abstract

In this research, two different models, i.e. adaptive-network-based fuzzy inference system (ANFIS) and autoregressive integrated moving average (ARIMA) were used to predict the quarterly GDP in Algeria during the period 1990 to 2019. The comparison shows that the ANFIS1 model provides better accuracy than the ARIMA(1,1,1) model in the quarterly forecast of GDP in Algeria. This is based on the quality prediction criterion of Root Mean Square Error (RMSE).