The analysis of the volatility in the exchange rate has long been a vital challenges and important topic in international finance. Because it is influenced by many factors and forces, while linear models are not able to capture nonlinear techniques and methods have been evolved in the last few decades for exchange rate prediction to overcome the limitations of the linear methods as well as the development of artificial intelligence, which has led to the development of alternative solutions utilizing non-linear modelling. This paper aims to use Artificial Neural Networks (ANN) to predict the value of the Egyptian pound in terms of US dollars, by depending on fundamental economic variables. The study concluded that the mean absolute percentage error (MAPE) is 2.8%. This result indicates that neural networks is accurate by 97.2% in forecasting exchange rate depends on the macroeconomic variables.