The Application of Artificial Neural Networks Techniques to the Prediction of Ringgit Exchanges Rates

This research examines and analyzes the use of neural networks as a forecasting tool. Specifically a neural network's ability to predict future trends of foreign exchange rates is tested. Accuracy is compared against a traditional forecasting methods, multiple linear regression analysis. Time series data and technical indicators are fed to neural nets to capture the underlying 'rules' of the movement in currency exchange rates. Three neural network models; Multi-layer Perceptron, Radial Basis Function and recurrent neural networks forecast the exchange rates between Ringgit Malasia and for other major currencies, Japanese Yen, Yuan, British Pound and Deutch Mark are desorbed. The four currencies were chosen because all the main volumes of operations on Forex are made with these currencies. Obtained results show that neural networks are able to give forecast with coefficient of multiple determinations. It was concluded that neural networks do have the capability to forecast financial markets and of properly trained the individual investor could benefit from the use of this forecasting tool.