因子分析和神经网络相融合的股票价格预测  

Stock Price Prediction Based on Factor Analysis and Neural Network

作　　者：郑睿[1] 周丽[1] 

机构地区：[1]郑州科技学院信息工程学院,河南郑州450064

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2015年第4期452-456,共5页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：国家自然科学基金青年基金资助项目(61202207)

摘　　要：为了提高股票价格的预测精度,提出一种因子分析与神经网络相融合的股票价格预测模型.首先采用因子分析法确定影响股票价格的主要因子,然后将主要因子作为神经网络的输入向量进行学习和建模,并采用遗传算法对神经网络进行优化.该模型融合了因子分析和神经网络的优势,可以准确刻画股票价格变化的复杂性和非平稳性,提高了股票价格的预测精度,而且泛化能力更优.In order to improve the prediction accuracy of the stock price,a stock price prediction model is proposed by fusing factor analysis and neural network.First of all,factor analysis method is used to an-alyze the influence factors of stock price and determine the main factors of the stock price,and secondly the main factors are taken as the input vectors of neural network to learn and model,and genetic algorithm is used to optimize neural network,finally the simulation experiment is used to test the performance by u-sing specific stock price data.The simulation results show that,compared with the current popular stock price prediction models,the proposed model can more accurately reflect the trend of stock price and can obtain better ideal the prediction results of stock price.

关 键 词：股票价格 预测模型 因子分析 神经网络 

分 类 号：O29[理学—应用数学] TP183[理学—数学]