عنوان مقاله [English]
This paper investigates model estimation and forecasting of exchange rate using artificial neural networks. 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, in a technical approach, ARIMA and artificial neural networks have been used for short-term forecast of daily USD to Rial exchange rate. ANN is employed in training and learning processes and then the forecast performance is measured making use of two common loss functions. The comparison demonstrates that an artificial neural network performs far better than ARIMA, with an error rate of about half.
Thereafter, in a fundamental approach via another neural network the effects of some of the most important economic variables on exchange rate prediction in a long-term sense are studied. By sensitivity analysis, the importance and the weight of each economic variable on exchange rate is calculated. The results show that it is possible to estimate a model to forecast the value of exchange rate even by having access to a limited subset of data.