This paper is based on research applying artificial intelligence to problems of trading financial markets. The paper presents a background to various financial market trading problems of interest. A model system and strategy for developing decision support systems to trade financial markets and forecast asset price movements is then presented and discussed. The problems of interest are those where the variables are not constant in time. The time series of data representing the dynamics of price move,ents in financial markets are non-linear and nonstatonary. The forecasting techniques developed are applied to examples of foreign exchange trading involving the directional movement only of the four major courrencies of British Pond Sterling, Deutschemark, Swiss Franc and Japanese Yen against be US Dolalr. Examples demonstrate the forecasting output and performance of the models as measured by live trading profit and loss returns.
展开▼
