灰色神经网络在股票价格预测中的应用

研究股票价格预测问题,股票价格具非线性和不确定性变化规律。传统单一模型只能反映股票价格部分信息,预测精度不高。为了提高股票价格预测精度,在分析股票价格变化特征基础上,提出一种灰色神经网络的股票价格预测方法。首先采用GM(1,1)模型对股票价格进行预测,捕捉其线性、灰色变化规律,然后采用BP神经网络对GM(1,1)预测残差进行建模预测,捕捉其非线性和不确定性变化规律,最后两者结果相加得到股票价格最终预测结果。将灰色神经网络用于浦发银行(60000)股票收盘价为例预测,结果表明,相于传统预测模型,灰色神经网络提高了股票价格预测精度,更能全面挖掘股票价格变化规律,在股票价格预测中具有广泛的应用前景。

Stock Prediction with Grey Neural Network Model

Study prediction of stock prices.Stock prices are of nonlinear,grey and uncertainty,so,single model can only reflect the stock price information,and prediction accuracy is not high.In order to improve the precision of prediction of stock price,based on the analysis of stock price changes,the paper put forward a kind of grey neural network method of stock price prediction.The GM(1,1) model was used to predict the stock price,capturing its linear and gray variation.Then,the BP neural network was used to predict error modeling and prediction,capturing the nonlinear and uncertain changes.Last,two results were combined to produce the final forecasting result of stock price.Grey neural network was used for the Shanghai Pudong Development Bank(60000) stock prediction,The results show that,relative to the traditional prediction model,the grey neural network can improve stock price prediction accuracy,mine more comprehensive stock price change rules,and has widespread application prospect in the prediction of stock prices.