The European Journal of Finance 1, 311-323 (1995) Leading edge forecasting techniques for exchange rate prediction IAN NABNEY\ CHRISTIAN DUNIS^ RICHARD DALLAWAY^, SWEE LEONG^ and WENDY REDSHAW" ^Aston University, ^Chemical Bank. 125 London Wall, London EC2Y 5AJ^Fusion Systems, "^Summit Financial Systems Limited This paper describes how modern machine lecirning techniques can be used in conjunction with statistical methods to forecast short term movements in exchange rates, producing models suitable for use in trading. It compares the results achieved by two different techniques, and shows how they can be used in a complementary fashion. The paper draws on experience of both inter- and intra-day forecasting taken from earlier studies conducted by Logica and Chemical Bank Quantitative Research & Trading (QRT) group's experience in developing trading models. In evaluating different models both trading performance and forecasting accuracy are used as measures of perform ance. Rule induction is a method for deriving classification rules from data. Logica's data exploration toolkit DataMakinkr™, which combines rule induction with statistical techniques, has been used successfully to model several exchange rate time series. An attractive feature of this approach is that the trading rules produced are in a form that is familiar to analysts. We also show how DataMariner^" can be used to determine the importance of different technical indicators and to understand relationships between different markets. This understanding can then be used to assist in building models using other analytical tools. Neural networks are a general technique for detecting and modelling patterns in data. We describe the principles of neural networks, the data pre processing that they require and our experience in training them to forecast the direction and magnitude of movements in time series. Keywords: machine learning techniques, leading-edge forecasting, rule Induction, neural networks. 1 I N T R O D U C T I O N This paper describes how modern machine learning techniques can be used in conjunction with statistical methods to forecast short term movements in exchange rates, producing models suitable for use in trading. It compares the results achieved by two different techniques and shows how they can be used in a complementary fashion. The two techniques used were rule induction, which is a method of extracting classification rules from data, and neural networks, which afford powerful and general methods for nonlinear function modelling. 1351-847X © 1995 Chapman & Hall