V. Lavanya, M. Parveentaj
Abstract: FOREX (Foreign Currency Exchange) is concerned with the exchange rates of foreign currencies compared to one another. It is needed for currency trading in the international market. One popular technique for predictions of financial market performance is Artificial Neural Networks (ANN), we proposed to do so with the back propagation algorithms. ANN is actually an information processing system that consists of a graph representing the processing system as well as various algorithms. It is able to adapt, to recognize patterns, to generalize, and to cluster or to organize data. Recently ANN can be trained to solve problems that are difficult when using conventional programming techniques or through the efforts of human beings. In order for ANN to recognize patterns in the data, it is necessary for the neural network to learn the structure of the data set. Learning is accomplished by providing sets of connected input/output units where each connection has a weight associated with it. The ANN learns by adjusting the weights so that the application of a set of inputs produces the desired set of outputs. Finally we proposed to show the best algorithm for FOREX prediction by comparing the effectiveness of various back propagation algorithm using Matlab neural network software as a tool.
Keywords: FOREX, Back propagation algorithm, Training function, neural network