Neural Network for Forecasting High Price and Low Price on Foreign Exchange Market

Abstract

This research compares 4 neural networks from the original researches (I. Backpropagation Neural Network II. Bayesian Regularized Neural Network III. Empirical Mode Decomposition Stochastic Time Strength Neural Network IV. Random Data-time Effective Radial Basis Function Neural Network) and 2 proposed neural networks (I. Empirical Mode Decomposition Random Data-time Effective Radial Basis Function Neural Network II. Empirical Mode Decomposition Random Data-time Effective Bayesian Regularized Neural Network) for predicting the exchange rate of EUR/USD currency pairs using input as a technical indicator and evaluating the networks with trading simulations consisting of investment strategies, risk management methods and financial management principles. The experiments show that the proposed neural networks yield higher returns than the original researches.