【摘要】 运用前馈神经网络预测时间序列的分析方法对股票数据进行了预测.通过对前馈神经网络时间序列数据预测网络模型的建立方法及预测方法讨论,基于BP网络对股票数据进行实际预测.预测精度明显高于传统方法,说明此种方法是可行的.BP网络可用于股票数据预测,其预测精度较高,但实际预测时,如何选择和确定一个合适的神经网络结构需进行反复实验.更多还原

【Abstract】 Study on prediction of stock data based on feedforward neural network′s time series prediction. Establishing of prediction network model in multiplayer feedforward neural network′s time series prediction and the prediction design measures are discussed, based on BP network the stock data are forecasted. The precision of prediction is higher than the traditional methods. It shows that the method is receivable. BP network can be used to prediction of stock data and the precision of prediction is high. But in practice, how to select and establish appropriate neural network is needed experiment repeatedly.更多还原