Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (5): 280-286.DOI: 10.3778/j.issn.1002-8331.2108-0104

• Engineering and Applications • Previous Articles     Next Articles

Stock Price Prediction Based on MDT-CNN-LSTM Model

CAO Chaofan, LUO Zenan, XIE Jiaxin, LI Lu   

  1. School of Mathematics, Physics and Statistics, Shanghai University of Engineering Science, Shanghai 201600, China
  • Online:2022-03-01 Published:2022-03-01



  1. 上海工程技术大学 数理与统计学院,上海 201600

Abstract: Stock price prediction has always been the focus of investors’ attention in the stock market. In recent years, deep learning technology has been widely used in this field. Based on the fusion of convolutional neural network(CNN) and long-short-term memory network(LSTM) to build a CNN-LSTM model, it introduces multi-directional delay embedding tensor processing technology MDT(mutiway-delay-embedding), daily stocks factor vector is subjected to factor reconstruction to generate the Hankel matrix, and the Hankel tensor is generated side by side in time as the input of the CNN-LSTM model. The convolution and pooling of CNN are used to extract features from the input data containing factor correlation information, and then the output feature matrix is input to the LSTM model for correlation prediction, thereby constructing the MDT-CNN-LSTM hybrid model. 48 companies and 12 stock factors involved in 22 industries are selected for stock price forecasting. Through comparative experiments in terms of forecasting accuracy and timeliness, it is shown that the proposs method performs better than other models. Finally, four types of stock indexes are selected for forecasting. The model effect is still at a relatively good level, which verifies the effectiveness and feasibility of the introduction of MDT technology.

Key words: stock price prediction, multi-directional delayed embedding(MDT), convolutional neural network(CNN), long-short-term memory network(LSTM)

摘要: 股价预测一直是投资者在股票市场中关注的焦点。近年来,深度学习技术在这一领域得到广泛应用。在融合卷积神经网络(CNN)和长短时记忆网络(LSTM),构建CNN-LSTM模型的基础上,引入多向延迟嵌入的张量处理技术MDT(mutiway-delay-embedding),对每日股票因子向量进行因子重构,生成汉克尔矩阵,按时间并排生成汉克尔张量,作为CNN-LSTM模型的输入。利用CNN的卷积与池化对包含因子相关性信息的输入数据提取特征,再将输出的特征矩阵输入到LSTM模型进行关联预测,从而构建了MDT-CNN-LSTM混合模型。选取涉及22个行业的48家公司及12个股票因子进行股价预测,通过从预测精度和时效性两个方面对比实验,显示提出的方法表现优于其他模型,最后选取四类股票指数进行预测,模型效果依旧处于较优水准,验证了引入MDT技术的有效性和可行性。

关键词: 股票价格预测, 多向延迟嵌入(MDT), 卷积神经网络(CNN), 长短时记忆网络(LSTM)