A quantitative venture capital strategy based on LASTM-DP
DOI:
https://doi.org/10.54691/bcpbm.v18i.580Keywords:
Quantitative Trading LSTM-EMA, Dynamic Programming, Analytic Hierarchy ProcessAbstract
With the development of quantitative trading technology such as deep learning, more and more investors participate in quantitative trading. LSTM (long short term memory network) belongs to one of the deep learning models, which has better performance in predicting time series data. Therefore, this paper takes the mixed trading strategy of gold and bitcoin from 2018 to 2021 as the research object, forecasts the price through LSTM-EMA algorithm, uses dynamic programming to solve the optimal investment strategy, finally constructs the factors to measure the investment risk by using data mining method, calculates the daily investment risk by using analytic hierarchy process, and combines it with the obtained strategy to effectively reduce the volatility of daily income, At the same time, the annualized yield of the final strategy was increased to 39.9%, leading the vast majority of fund returns in the same period.
Downloads
References
Hu Juzhou, LAN Qiujun. Comparison between data mining technology of financial time series and classical statistical model [J]. Systems engineering, 2005, 23 (6): 95-98.
Fang Yiqiu, Lu Zhuang, Ge Junwei Stock price prediction of joint RMSE loss lstm-cnn model [J] Computer engineering and application: 1-10.
Wang Ting, Xia yangyuxin, Chen Tieming, stock short-term trend prediction based on multi category feature system [J] Computer science, 2020,47 (S2): 491-495.
Hochreiter S and Schmidhuber J. Long short-term memory. [J]. Neural computation, 1997, 9(8): 1735-80.
Wu Dashuo, Zhang chuanlei, Chen Jia, Xiang Qihuai Prediction and analysis of stock index based on improved LSTM neural network based on genetic algorithm [J] Computer application research, 2020,37 (S1): 86-87 + 107.
Kumar K, Haider M T U. Enhanced Prediction of Intra-day Stock Market Using Metaheuristic Optimization on RNN-LSTM Network [J]. New Generation Computing, 2021, 39(1): 231-272.
Murphy J. Technical analysis of the futures market [M]. London: Prentice Hall Press,1986.
Christian Pierdzioch and Marian Risse and Sebastian Rohloff. On the efficiency of the gold market: Results of a real-time forecasting approach [J]. International Review of Financial Analysis, 2014, 32: 95-108.
Zhao Xiaoli Research on optimal pension investment strategy based on dynamic method [D] China University of metrology, 2018.
Apoorv Gupta and Prabina Rajib. Do VaR exceptions have seasonality? An empirical study on Indian commodity spot prices [J]. IIMB Management Review, 2018, 30(4): 369-384.
Madhusudan Karmakar and Samit Paul. Intraday portfolio risk management using VaR and CVaR: A CGARCH-EVT-Copula approach [J]. International Journal of Forecasting, 2019, 35(2): 699-709.
Shen Liangfeng, fan Xiangru Evaluation and decision-making of venture capital projects based on analytic hierarchy process [J] Infrastructure optimization, 2002, (04): 20-22.
Downloads
Published
Issue
Section
