A Genetic Algorithm Combined with Neural Networks in Forecasting Shanghai Stock Market of China

摘要

Neural networks have been widely used to forecast indices and prices of stock market due to the significant properties of treating non-linear data with self-learning capability. However, common neural networks often suffer from long convergent processes and occasionally involve in a local optimal solution that more or less limited their applications in practice. To overcome the drawbacks of the common neural networks, a new genetic algorithm combined with artificial neural network (GANN) is developed in this study. The results of a positive analysis based on comprehensive index of Shanghai stock market in China indicate that the forecasting performances of the proposed genetic neural network are much better than ones of the common neural network. It seems that the proposed genetic neural network may be an efficient forecasting system in financial time series. To make the process clearer, a numerical example is demonstrated for illustration.