摘要
根据中国股票市场的随机波动性特点,提出一种基于灰关联神经网络与马尔可夫模型的股票价格预测模型.首先利用灰色关联分析来遴选反映价格波动趋势的关键性技术指标,然后利用误差后向传播的人工神经网络对收盘价格作粗预测,最后再用马尔可夫模型对收盘价格作精预测.实验结果表明,与传统预测模型相比,该模型能有效地提高股票价格短期预测的精度,且计算复杂程度较低.
In order to find the changing trend of the stock price,a model is proposed based on the Grey correlation analysis theory,BP neural network and Markov theory.Firstly,Grey correlation analysis is used to select the best index of the stock price trend,which is used as the input parameters of BP neural network.And then the BP neural network is used to predict roughly the closing price.Finally,a high precision prediction of the closing price is realized by Markov model.Compared to the experimental model,the experimental results show that the model can improve the precision prediction and reduce the complexity of the short term forecast of the stock price.
出处
《内蒙古师范大学学报（自然科学汉文版）》
CAS
北大核心
2016年第3期310-314,共5页
Journal of Inner Mongolia Normal University(Natural Science Edition)
基金
国家自然科学基金资助项目(51179146)
教育部人文社科基金项目(12YJAZH022)
湖北省商务厅科研项目(HBSW-2014-01)
