Research on trading strategy based on improved LSTM network model
DOI:
https://doi.org/10.54691/bcpbm.v26i.1941Keywords:
Support vector machine; stochastic forest algorithm; sensitivity analysis.Abstract
The economic foundation determines the superstructure of society. Sustainable development of society is inseparable from economic prosperity, and investment has an irreplaceable role as one of the "troika" to promote social economy. Based on this, the modeling in this paper aims to study the trading strategy problem. In this paper, firstly, outliers and missing values are processed by Laiida's rule for the attached data, and then a multi-layer LSTM weighted model is proposed to learn the influencing factors of input time span on output time span by using multi-layer LSTM network, and the model is trained to achieve higher accuracy relative to the LSTM model through the embedded method: superposition of the influence generation cycle sequence. Attention mechanisms are introduced and short and long term forecasts are continuously made. The fluctuations of MACD, RSI indicators, Apriori and other parameters are quantified; then, a risk measurement index is constructed, where the greater the cyclical price fluctuations, the greater the risk. The results show that timely buying and selling maximizes returns, and that a $1,000 investment ends up with a $900,000 return. The model is run again by increasing or decreasing the percentage of transaction costs, setting 0.5%, 1%, 1.5% and 2% points, to test the magnitude of sensitivity (trading decision results) at different transaction costs. The results show that the model is more robust, i.e., the model constructed in this paper has better results under different transaction costs.
Downloads
References
Cao Wen. Empirical research on multi-factor stock selection based on XGBoost algorit-hm [D]. Shandong University of Finance and Economics, 2021.
Lü Mengdi. Design of quantitative stock selection trading strategy based on price-to-book ratio interpretation model and stochastic forest algorithm [D]. Shanghai Normal University, 2021.
Wu Bingxin. Research on multi-factor quantitative stock selection strategy based on Lig-htGBM [D]. Northwest University, 2021.
Xu Zhijian. Research on Quantitative Trading Stock Selection Strategy of Thirty-Three Degrees Asset Management Company Based on Machine Learning [D]. Lanzhou University of Technology, 2020.
Cai Gaoyuan. Research on quantitative investment model of large-scale assets based on machine learning [D]. Henan University, 2020.
Wang Huaqin. Quantitative stock selection and effect evaluation based on machine lear-ning [D]. University of Electronic Science and Technology of China, 2020.
Wei Jing. Research on Quantitative Investment Strategy Based on Integrated Algorithm [D]. Hebei University of Technology, 2020.
Hü gege. Industry Stratified Stock Selection Strategy Based on Convolutional Neural N-etwork [D]. University of Electronic Science and Technology of China, 2020.
ZHU Xiaoqiang. Quantitative multi-factor stock selection strategy of dynamic optimizati-on machine learning algorithm [D]. East China University of Political Science and Law, 2020.
Downloads
Published
Issue
Section
How to Cite
