Adaptive Neuro Fuzzy Inference Systems for High Frequency Financial Trading and Forecasting

The prediction of financial time series is a very complicated process. An initial look at financial time series gives the impression that they are random in nature. If true, this would make the forecast, and therefore the trading, of such series exceptionally difficult. The efficient market hypothesis states that the current price contains all available information in the market. This leads to the predictability of most financial time series as being a rather controversial issue. Experts have been forecasting and trading financial markets for decades, using their knowledge and expertise in recognizing patterns and interpreting current financial data. This paper extends the Adaptive Neuro-Fuzzy Inference System to create an expert system that is capable of using fuzzy reasoning combined with the pattern recognition capability of neural networks to be used in financial forecasting and trading. The novelty of the approach lies in its application to the field of high frequency finance. Such an approach has not been used so far with high frequency trading or as a part of an automated trading strategy. This has produced an expert trading system which overcomes the physical limitations of human experts and traders in taking multiple decisions at extremely short time intervals. This means the system can perform predictions and trading decisions at a very high frequency using intra-day data.