CNN-LSTM Neural Network Model for Quantitative Strategy Analysis in Stock Markets

被引:67
作者
Liu, Shuanglong [1 ,2 ]
Zhang, Chao [3 ]
Ma, Jinwen [1 ,2 ]
机构
[1] Peking Univ, Dept Informat Sci, Sch Math Sci, Beijing 100871, Peoples R China
[2] Peking Univ, LMAM, Beijing 100871, Peoples R China
[3] Peking Univ, Acad Adv Interdisciplinary Studies, Beijing 100871, Peoples R China
来源
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT II | 2017年 / 10635卷
关键词
Neural network; CNN; LSTM; Quantitative strategy; Stock markets;
D O I
10.1007/978-3-319-70096-0_21
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, the convolutional neural network and long short-term memory (CNN-LSTM) neural network model is proposed to analyse the quantitative strategy in stock markets. Methodically, the CNN-LSTM neural network is used to make the quantitative stock selection strategy for judging stock trends by using the CNN, and then make the quantitative timing strategy for improving the profits by using the LSTM. It is demonstrated by the experiments that the CNN-LSTM neural network model can be successfully applied to making quantitative strategy, and achieving better returns than the basic Momentum strategy and the Benchmark index.
引用
收藏
页码:198 / 206
页数:9
相关论文
共 16 条
  • [1] [Anonymous], 2017, IEEE transactions on neural networks and learning systems, DOI DOI 10.1109/TNNLS.2016.2582924
  • [2] Bouvrie J., 2006, Notes on convolutional neural networks
  • [3] Intelligent technical analysis based equivolume charting for stock trading using neural networks
    Chavarnakul, Thira
    Enke, David
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2008, 34 (02) : 1004 - 1017
  • [4] Ding X, 2015, PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI), P2327
  • [5] Forecasting non-stationary time series by wavelet process modelling
    Fryzlewicz, P
    Van Bellegem, S
    von Sachs, R
    [J]. ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2003, 55 (04) : 737 - 764
  • [6] Fu C., 2004, TECHNOL DEV ENTERP, V4, P005
  • [7] Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
  • [8] RECEPTIVE FIELDS AND FUNCTIONAL ARCHITECTURE OF MONKEY STRIATE CORTEX
    HUBEL, DH
    WIESEL, TN
    [J]. JOURNAL OF PHYSIOLOGY-LONDON, 1968, 195 (01): : 215 - &
  • [9] Gradient-based learning applied to document recognition
    Lecun, Y
    Bottou, L
    Bengio, Y
    Haffner, P
    [J]. PROCEEDINGS OF THE IEEE, 1998, 86 (11) : 2278 - 2324
  • [10] Stock Price Prediction Through the Mixture of Gaussian Processes via the Precise Hard-cut EM Algorithm
    Liu, Shuanglong
    Ma, Jinwen
    [J]. INTELLIGENT COMPUTING METHODOLOGIES, ICIC 2016, PT III, 2016, 9773 : 282 - 293