Forecasting Stock Price Using a Genetic Fuzzy Neural Network

The use of neural networks (NNs) for stock market forecast is quite common because of their excellent performances of treating non-linear data with self-learning capability. However, neural networks suffer from the difficulty to deal with qualitative information and the "black box" syndrome that more or less limited their applications in practice. The fuzzy neural networks (FNN) allow to add rules to neural networks. This avoids the "black-box" but lacks of effective learning capability. To overcome these drawbacks, in this study an integration of genetic algorithm and fuzzy neural networks (GFNN) are proposed to forecast stock price. The results indicate that the predictive accuracies obtained from GFNN are much higher than the ones obtained from NNs. To make this clearer, an illustrative example is also demonstrated in this study.