Swingler K (1996) Financial prediction: Some pointers, pitfalls and common errors. Neural Computing and Applications, 4 (4), pp. 192-197. https://doi.org/10.1007/BF01413817
There is growing interest both in the field of neural computing and in the financial world in the possibility of using neural networks to forecast the future changes in prices of stocks, exchange rates, commodities and other financial time series. Since networks have been shown to be capable of modelling the underlying structure of a time series, many attempts have been made at exploiting that capability in order to carry out a technical analysis of such prices. If the efficient markets hypothesis is true, however, there is no underlying structure to be modelled, and the whole endeavour is doomed to failure. This paper investigates the common methods for such an approach, and outlines the major pitfalls and common errors to avoid. The author hopes that by pointing out the possible pitfalls now, we can avoid making claims to the commercial world before we are properly ready to do so.
efficient markets hypothesis; financial forecasting; recurrent networks; result verification; time delay neural networks; time series analysis
Neural Computing and Applications: Volume 4, Issue 4