Research on Neural Network Based on the Improved Adaptive Genetic Algorithm

Considering the problem of the local optimization in the adaptive genetic algorithm (AGA), this paper presents an improved adaptive genetic algorithm (IAGA) which can optimize the weights and thresholds of the neural network. A stock prediction system based on neural networks and fuzzy theory is designed. According to the analysis of the history data of the stock, the system predicts this stock´s market trend of the following days and makes the decision support for the investors on the stock´s market. The experimental results show that the proposed approach has high accuracy, strong stability and improved confidence.