| Citation: |
ZHANG Peng, YANG Yang, LI Jingxin, ZENG Yongquan. A Two-stage Mean-CVaR Investment Strategy Based on LSTM[J]. Journal of South China Normal University (Natural Science Edition), 2023, 55(5): 93-102. DOI: 10.6054/j.jscnun.2023068
|
A novel dual-stage mean-CVaR investment strategy based on long-short term memory networks (LSTM) is proposed, namely, LSTM+CVaR model. Specifically, in the first stage, the LSTM is used to predict the return of stocks and select stocks. In the second stage, the mean-CVaR model is used to determine the weight of every stock. Finally, using China Securities 300 Index component stocks as sample, considering the influence of threshold constraints and transaction costs, the characteristics of risk and return, cumulative return and Sharpe Ratio of portfolio models are compared in this paper, and the portfolio models include LSTM+CVaR model, equal weight model based on LSTM prediction, CVaR model based on random stock selection, equal weight model based on random stock selection and China Securities 300 Index component stocks. The empirical results demonstrate that the LSTM+CVaR model achieves higher average returns, return-risk ratio, cumulative returns, Sharpe Ratio, and decreasing the transaction costs or increasing the threshold constraint can improve the performance of the above model.
| [1] |
GUNDUZ H, YASLAN Y, CATALTEPE Z. Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations[J]. Knowledge-Based Systems, 2017, 137: 138-148. doi: 10.1016/j.knosys.2017.09.023
|
| [2] |
ERSAN D, NISHIOKA C, SCHERP A. Comparison of machine learning methods for financial time series forecasting at the examples of over 10 years of daily and hourly data of DAX 30 and S&P 500[J]. Journal of Computational Social Science, 2020, 3(1): 103-133. doi: 10.1007/s42001-019-00057-5
|
| [3] |
VO N N Y, HE X Z, LIU S, et al. Deep learning for decision making and the optimization of socially responsible investments and portfolio[J]. Decision Support Systems, 2019, 124: 113097/1-11. doi: 10.1016/j.dss.2019.113097
|
| [4] |
JIANG W W. Applications of deep learning in stock market prediction: recent progress[J]. Expert Systems with Applications, 2021, 184: 115537/1-22. doi: 10.1016/j.eswa.2021.115537
|
| [5] |
梁姝娜, 张友祥, 王学稹. 基于BP神经网络和Logistic模型的中国人均粮食产量预测研究[J]. 华南师范大学学报(社会科学版), 2015(5): 102-106.
|
| [6] |
SONG Y, LEE J W, LEE J. A study on novel filtering and relationship between input-features and target-vectors in a deep learning model for stock price prediction[J]. Applied Intelligence, 2019, 49: 897-911. doi: 10.1007/s10489-018-1308-x
|
| [7] |
HOSEINZADE E, HARATIZADEH S. CNNpred: CNN-based stock market prediction using a diverse set of variables[J]. Expert Systems with Applications, 2019, 129: 273-285. doi: 10.1016/j.eswa.2019.03.029
|
| [8] |
DING G Y, QIN L X. Study on the prediction of stock price based on the associated network model of LSTM[J]. International Journal of Machine Learning and Cybernetics, 2019, 11(6): 1307-1317.
|
| [9] |
MINH D L, SADEHI-NIARAKI A, HUY N D, et al. Deep learning approach for short-term stock trends prediction based on two-stream gated recurrent unit network[J]. IEEE Access, 2018, 6: 55392-55404. doi: 10.1109/ACCESS.2018.2868970
|
| [10] |
杨青, 王晨蔚. 基于深度学习LSTM神经网络的全球股票指数预测研究[J]. 统计研究, 2019, 36(3): 65-77.
YANG Q, WANG C W. A study on forecast of global stock indices based on deep LSTM neural network[J]. Statistical Research, 2019, 36(3): 65-77.
|
| [11] |
SU Z, XIE H L, HAN L. Multi-factor RFG-LSTM algorithm for stock sequence predicting[J]. Computer Economics, 2021, 57: 1041-1058. doi: 10.1007/s10614-020-10008-2
|
| [12] |
MARKOWITZ H. Portfolio selection[J]. The Journal of Finance, 1952, 7(1): 77-91.
|
| [13] |
GAO J, LI D, CUI X Y, et al. Time cardinality constrained mean-variance dynamic portfolio selection and market timing: a stochastic control approach[J]. Automatica, 2015, 54: 91-99. doi: 10.1016/j.automatica.2015.01.040
|
| [14] |
张鹏, 曾永泉. 具有卖空总量限制的多阶段M-SAD投资组合优化[J]. 中国管理科学, 2021, 29(6): 60-69.
ZHANG P, ZENG Y Q. Multiperiod mean semi-absolute deviation portfolio selection with total short selling constraints[J]. Chinese Journal of Management Science, 2021, 29(6): 60-69.
|
| [15] |
STOILOV T, STOILOVA K, VLADIMIROV M. The probabilistic risk measure VaR as constraint in portfolio optimization problem[J]. Cybernetics and Information Techno-logies, 2021, 21(1): 19-31. doi: 10.2478/cait-2021-0002
|
| [16] |
ROCKAFELLAR R T, URYASEV S P. Conditional Value-at-Risk for general loss distributions[J]. Journal of Ban-king & Finance, 2002, 26(7): 1443-1471.
|
| [17] |
XU Q F, ZHOU Y Y, JIANG C X, et al. A large CVaR-based portfolio selection model with weight constraints[J]. Economic Modelling, 2016, 59: 436-447. doi: 10.1016/j.econmod.2016.08.014
|
| [18] |
HUANG D S, ZHU S S, FABOZZI F J, et al. Portfolio selection under distributional uncertainty: a relative robust CVaR approach[J]. European Journal of Operational Research, 2010, 203(1): 185-194.
|
| [19] |
张鹏. 不允许卖空情况下均值-方差和均值-VaR投资组合比较研究[J]. 中国管理科学, 2008, 16(4): 30-35.
ZHANG P. The comparison between mean-variance and mean-VaR Portfolio models without short sales[J]. Chinese Journal of Management Science, 2008, 16(4): 30-35.
|
| [20] |
PAIVA F D, CARDOSO R T N, HANAOKA G P, et al. Decision-making for financial trading: a fusion approach of machine learning and portfolio selection[J]. Expert Systems with Applications, 2019, 115: 635-655.
|
| [21] |
ZHANG J, TENG Y F, CHEN W. Support vector regression with modified firefly algorithm for stock price forecasting[J]. Applied Intelligence, 2019, 49(5): 1658-1674.
|
| [22] |
LI L L, ZHAO X, TSENG M L, et al. Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm[J]. Journal of Cleaner Production, 2020, 242: 118447/1-12.
|
| [23] |
CHEN W, ZHANG H Y, MEHLAWAT M K, et al. Mean-variance portfolio optimization using machine learning-based stock price prediction[J]. Applied Soft Computing, 2021, 100(1): 106-943.
|
| 1. |
何乃如，田子谕，王伟，桓茜，靳浩斌，白帅丽. 甘蔗生物质炭在界面太阳能海水淡化中的应用. 华南师范大学学报(自然科学版). 2024(01): 44-52 .
| |
| 2. |
谭春林，王维朗，徐志武，王建平. 生成式人工智能赋能科技论文视频摘要的实践与挑战. 中国科技期刊研究. 2024(12): 1767-1774 .
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: