ABSTRACT
Asset price forecasting is essential for portfolio decision-making. This paper establishes an asset price prediction model based on LSTM neural network to achieve asset price prediction. First, the historical asset price dataset is used as the training set of the model, and this paper set two hidden layers with 50 and 80 neuron units, respectively. Second, the Adam optimizer is used for the second hidden layer to optimize the neural network and minimize the loss function. Finally, the output layer data of asset price prediction is obtained considering the environment and other factors to achieve accurate price prediction. Meanwhile, this paper constructs a Markowitz-Dynamic programming model based on Markowitz and dynamic programming theories. It uses the output data cost of the prediction model to establish optimal portfolio planning, optimize portfolio decisions, and maximize investment returns. The model shown in this paper has significant reference value for investors' portfolio decisions and is essential to help investors obtain higher investment returns to a greater extent.
- H. Markowitz, “Portfolio Selection,” The Journal of Finance, vol. 7, no. 1, pp. 77–91, 1952, doi: 10.2307/2975974.Google ScholarCross Ref
- “Stochastic Controls: Hamiltonian Systems and HJB Equations | Semantic Scholar.” https://www.semanticscholar.org/paper/Stochastic-Controls%3A-Hamiltonian-Systems-and-HJB-Yong-Zhou/f60223dee8815324a4b9df9d1825e7c33fc099f3Google Scholar
- Controlled Markov Processes and Viscosity Solutions, vol. 25. New York: Springer-Verlag, 2006. doi: 10.1007/0-387-31071-1.Google ScholarCross Ref
- “Optimal Portfolio Choice with Estimation Risk: No Risk-free Asset Case | Semantic Scholar.” https://www.semanticscholar.org/paper/Optimal-Portfolio-Choice-with-Estimation-Risk%3A-No-Kan-Wang/c21b48a1b2d126b238544b5452375bc27b6def85Google Scholar
- “Technical Note—A Robust Perspective on Transaction Costs in Portfolio Optimization | Operations Research.” https://pubsonline.informs.org/doi/abs/10.1287/opre.2017.1699Google Scholar
- “Robust multiobjective portfolio with higher moments - ScienceDirect.” https://www.sciencedirect.com/science/article/abs/pii/S0957417418300745Google Scholar
- F. A. Gers, J. Schmidhuber, and F. Cummins, “Learning to forget: continual prediction with LSTM,” in 1999 Ninth International Conference on Artificial Neural Networks ICANN 99. (Conf. Publ. No. 470), Sep. 1999, vol. 2, pp. 850–855 vol.2. doi: 10.1049/cp:19991218.Google ScholarCross Ref
- Y. Wu, M. Yuan, S. Dong, L. Lin, and Y. Liu, “Remaining useful life estimation of engineered systems using vanilla LSTM neural networks,” Neurocomputing, vol. 275, pp. 167–179, Jan. 2018, doi: 10.1016/j.neucom.2017.05.063.Google ScholarCross Ref
- “Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data | PLOS ONE.” https://journals.plos.org/plosone/article?id=10.1371%2Fjournal.pone.0212320Google Scholar
- “Study on the effective frontier of portfolio with transaction cost and risk aversion coefficient–《Journal of Science of Teachers’ College and University》” http://en.cnki.com.cn/Article_en/CJFDTOTAL-GLKX201708001.htm.Google Scholar
- Y. Yu, X. Si, C. Hu, and J. Zhang, “A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures,” Neural Comput, vol. 31, no. 7, pp. 1235–1270, Jul. 2019, doi: 10.1162/neco_a_01199.Google ScholarDigital Library
- R. Staudemeyer and E. Morris, Understanding LSTM – a tutorial into Long Short-Term Memory Recurrent Neural Networks. 2019.Google Scholar
- “Markowitz Revisited: Financial Analysts Journal: Vol 32, No 5.” https://www.tandfonline.com/doi/abs/10.2469/faj.v32.n5.47.Google Scholar
Index Terms
- Optimal Portfolio Model based on LSTM Neural Network and Markovitz Theory
Recommendations
Resource allocation neural network in portfolio selection
Portfolio selection is a resource allocation problem in a finance market. The investor's asset optimization requires the distribution of a set of capital (resources) among a set of entities (assets) with the trade-off between risk and return. The ANN ...
Investment Model Based on LSTM Network Forecasting and Portfolio Investment
ICEMC '22: Proceedings of the 2022 International Conference on E-business and Mobile CommerceIn recent years, Bitcoin has attracted more and more investors' attention. Different from traditional financial assets, the price of Bitcoin is extremely volatile. Therefore, investors need to choose an appropriate asset portfolio to hedge the risk of ...
Multi-agent reinforcement learning approach for hedging portfolio problem
AbstractDeveloping a hedging strategy to reduce risk of losses for a given set of stocks in a portfolio is a difficult task due to cost of the hedge. In Vietnam stock market, cross-hedge is involved hedging a long position of a stock because there is no ...
Comments