计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (3): 203-207.DOI: 10.3778/j.issn.1002-8331.1912-0448

• 模式识别与人工智能 • 上一篇    下一篇

基于LSTM-CNN-CBAM模型的股票预测研究

赵红蕊,薛雷   

  1. 上海大学 通信与信息工程学院,上海 200444
  • 出版日期:2021-02-01 发布日期:2021-01-29

Research on Stock Forecasting Based on LSTM-CNN-CBAM Model

ZHAO Hongrui, XUE Lei   

  1. College of Communication and Information Engineering, Shanghai University, Shanghai 200444, China
  • Online:2021-02-01 Published:2021-01-29

摘要:

为了更好地对股票价格进行预测,进而为股民提供合理化的建议,提出了一种在结合长短期记忆网络(LSTM)和卷积神经网络(CNN)的基础上引入注意力机制的股票预测混合模型(LSTM-CNN-CBAM),该模型采用的是端到端的网络结构,使用LSTM来提取数据中的时序特征,利用CNN挖掘数据中的深层特征,通过在网络结构中加入注意力机制——Convolutional Attention Block Module(CBAM)卷积模块,可以有效地提升网络的特征提取能力。基于上证指数进行对比实验,通过对比实验预测结果和评价指标,验证了在LSTM与CNN结合的网络模型中加入CBAM模块的预测有效性和可行性。

关键词: 长短期记忆网络(LSTM), 卷积神经网络(CNN), 注意力机制, 股价预测

Abstract:

In order to better predict stock prices and provide reasonable suggestions for stockholders, a hybrid stock prediction model(LSTM-CNN-CBAM) that incorporates attention mechanism based on Long Short and Term Memory(LSTM) network and Convolutional Neural Network(CNN) is proposed. The model uses an end-to-end network structure. LSTM is used to extract the time-series features in the data, and then CNN is used to mine the deep features in the data. By adding an attention mechanism to the network structure Convolutional Attention Block Module convolution module, which can effectively improve the feature extraction capability of the network. Based on the Shanghai Stock Exchange Index, a comparative experiment is performed. By comparing the experimental prediction results and evaluation indicators, the prediction effectiveness and feasibility of adding the CBAM module to the network model combining LSTM and CNN are verified.

Key words: Long Short and Term Memory(LSTM) network, Convolutional Neural Network(CNN);attention mechanism, stock price forecasting