The Effects of Economic Variables on Exchange Rate, Modeling and Forecasting: Case of Iran

Abstract

This paper investigates the model estimation and data forecasting of exchange rate using artificial neural network. Recent studies have shown the classification and prediction power of the neural networks. It has been demonstrated that a neural network can approximate any continuous function. In this research, ANN is employed in training and learning processes and after modeling, the forecast performance is measured by making use of a loss function (RMSE). By sensitivity analysis, the importance and the weight of each economic variable on exchange rate such as consumer price index, old price, oil price and total value of export and import have been determined. The results show that Iran consumer price index is the most effective factor on exchange rate trend. In addition to, it is possible to estimate a model to forecast the value of exchange rate even by having access to a limited subset of data.