股票市场是国民经济发展变化的"晴雨表",股票价格的涨跌也是政治、经济、社会等诸多因素的综合反映.近几年来,神经网络取得较大发展已经成为热点研究并在各个领域中得到应用.文章基于主成分分析和BP神经网络,以中国石化100天股票历史技术指标数据作为训练样本对收盘价进行预测,20天数据进行检验,并通过图像仿真拟合来验证神经网络股票预测的可行性和准确性.
The stock market is a "barometer" of the changes and development of national economic,the change of stock prices is also a reflection of comprehensive factors such as policics,economy economic and society.In recent years,neural network which has achieved greater development has become a hot research spot applied in various fields.In this paper,100 days' historical datas of Sinopec stock technical indicators as the training samples are used to predict the closing price and10 days' datas to test,which is based on principal component analysisand BP neural network.Finally,the feasibility and accuracy of neural network to predict the stock are verified by fitting the images.