Forecasting stock prices has been regarded as one of the most challenging applications of modern time series forecasting.
Thus, numerous models have been depicted to provide the investors with more precise predictions. Recently,
artificial neural networks (ANN) have been applied to solve problems of forecasting stock prices. Kimoto and Asakawa
[1] used modular neural networks to predict the timing of buying and selling for the Tokyo Stock Exchange. Experimental
results showed that an excellent profit was achieved.
Kamijo and Tanigawa [2] developed a pattern recognition technique to predict the stock prices on the Tokyo Stock Exchange.
A new method has been presented to evaluate the recurrent networks to decrease the mismatching patterns.