Comparison of Neural Network Models, Vector Auto Regression (VAR), Bayesian Vector-Autoregressive (BVAR), Generalized Auto Regressive Conditional Heteroskedasticity (GARCH) Process and Time Series in Forecasting Inflation in Iran
Subject Areas : International Journal of Industrial Mathematics
1 - Department of Agriculture Economy, University of Tehran, Tehran, Iran.
2 - Department of Accounting, Ghiyamdasht Branch, Islamic Azad University, Ghiyamdasht, Iran.
Keywords: Inflation, Forecast, Neural Network, Vector auto regression, Bayesian Vector-Autoregressiv, GARCH, Time series.,
Abstract :
This paper has two aims. The first is forecasting inflation in Iran using Macroeconomic variables data in Iran (Inflation rate, liquidity, GDP, prices of imported goods and exchange rates) , and the second is comparing the performance of forecasting vector auto regression (VAR), Bayesian Vector-Autoregressive (BVAR), GARCH, time series and neural network models by which Iran's inflation is forecasted. The comparison of performance of forecasting models used to forecast Iran's inflation has been done based on the Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) of the models. Due to the annual values of Inflation, liquidity, GDP, prices of imported goods and exchange rates at free market to estimate different models in this paper and compare root mean square error and Mean Absolute Percentage Error of models by which inflation has been forecasted, neural network model had better performance than others models in forecasting Iran's inflation. Indeed root mean square error and Mean Absolute Percentage Error of neural network model have less value rather than root mean square error and Mean Absolute Percentage Error of other forecasting models.