A Model for Trading the Foreign Exchange Market

Abstract

The electronic Foreign Exchange (FOREX) market where currencies are bought and sold has become more complex and dynamic with characteristics of high volatility, nonlinearity, and irregularity. Some important factors such as economic growth, trade development, interest rates, inflation rates, etc. have significant impacts on the exchange rate fluctuation. Existing foreign exchange (FOREX) trading models have been found inadequate. They have tended to use only past price data and appear to be too stochastic or too deterministic. In this work an improved model that provides a wide set of dynamic process information has been developed. Technical and fundamental methods of analysis of FOREX market data were modeled with neural networks. The predictions from the networks are integrated to get the direction of price movement. Market sentiment and volatility values are combined with the neural network prediction to develop trading strategies using Marcov chain. Finally, an application of the model in FOREX trading is demonstrated and implemented with the Meta-Quote scripting Language (MQL) of the meta-Trader platform. The historical test of the robot for the last 12 months resulted in a range of significant profitability with annual returns between 40% to700% and with maximum relative draw down risk between 8% to 52%

Keywords: FOREX, marcov chain, model, neural network, trading robot