关键词: 神经网络, 灰色模型, 股票价格, 预测, 修正

Abstract: The stock price is influenced by many factors. The change has tendency, large fluctuation and stochastic characteristics. This paper proposes a stock price prediction model based on gray theory and BP neural network. The stock price based changes are simulated by the grey GM（1，1） prediction model, and the grey GM（1，1） model prediction results are modified by BP neural network to improve the prediction precision of the stock price. The model performance is tested by 60 000 stock prices. The results show that the proposed model can greatly improve the prediction precision of the stock price; it can mine the stock price changes.

Key words: neural network, GM（1, 1）, stock price, prediction, modification