期刊文献+

基于近端强化学习的股价预测方法 被引量:4

Method of stock prices forecast based on proximal reinforcement learning
原文传递
导出
摘要 股价预测一直是金融时间序列研究的热点和难点,采用一种合理有效的股价预测方法对于投资者获取高额收益回报及规避交易风险具有重要的指导意义.通过结合近端策略优化(proximal policy optimization, PPO)和强化学习(reinforcement learning, RL),将股价预测视为一个时间序列预测问题,提出一种近端强化学习的股价预测方法 (PPORL).此外,在预测方法的基础上引入股票的相对强弱性能和股票均线指标,提出一种能够自动捕捉潜在交易点的量化交易策略,期望在获取高额收益的同时降低交易过程中存在的风险.通过实验对比了长短期记忆网络(long short-term memory, LSTM)和循环神经网络(recurrent neural network, RNN)模型在上证指数(SZZS)、深证成指(SZCZ)和沪深300指数(HS300)上的预测性能和交易决策表现,并利用多种误差评估方法对预测结果进行定量分析,从而验证了PPORL在预测性能和交易决策等方面的有效性和鲁棒性. Stock prices forecast is a hot and challenging topic in financial time series research. It is of great significance for the investors in theirs stock trading, to maximize revenue and to avoid risks by adopting a reasonable and effective forecasting method. A stock prices forecast method based on proximal reinforcement learning which combines proximal policy optimization(PPO) and reinforcement learning(RL), namely PPORL, is proposed, and the forecasting process is regarded as a time series prediction problem. Furthermore, the relative strength index(RSI) and move average of five days(MA5) are also introduced working as a trading strategy, which can automatically capture potential trading points,and avoid trading risks. By comparing the prediction performance and trading decision performance with long short-term memory(LSTM) and recurrent neural network(RNN) models on the SSE composite index(SZZS), the SZSE component index(SZCZ) and the CSI300 index(HS300), and a variety of error evaluation methods are used for quantitative analysis of the prediction results, which shows the effectiveness and robustness of the PPORL in forecasting performance and trading decision.
作者 岑跃峰 张晨光 岑岗 赵澄 CEN Yue-feng;ZHANG Chen-guang;CEN Gang;ZHAO Cheng(School of Information and Electronic Engineering,Zhejiang University of Seience and Technology,Hangzhou 310023,China;School of Economics,Zhejiang University of Technology,Hangzhou 310023,China)
出处 《控制与决策》 EI CSCD 北大核心 2021年第4期967-973,共7页 Control and Decision
基金 国家自然科学基金项目(61902349) 教育部规划基金项目(17YJA880004) 浙江省科技计划项目(2017C31038) 浙江省教育厅一般科研项目(Y201839557)。
关键词 股价预测 机器学习 近端优化 强化学习 时间序列 量化交易 stock prediction machine learning proximal optimization reinforcement learning time series quantitative trading
  • 相关文献

参考文献3

二级参考文献20

  • 1张森,肖先赐.混沌时间序列全局预测新方法——连分式法[J].物理学报,2005,54(11):5062-5068. 被引量:25
  • 2Tongal H, Berndtsson R. Phase-space reconstruction and self-exciting threshold modeling approach to forecast lake water levels[J]. Stoch Environ Res Risk Assess, 2014, 28(4): 955-971.
  • 3Masoumi H R F, Basri M, Kassim A, et al. Comparison of estimation capabilities of the artificial neural network with the wavelet neural network in lipase-catalyzed synthesis of triethanolamine-based esterquats cationic surfactant[J]. J of Surfact Deterg, 2014, 17(2): 287-294.
  • 4Pandey A, Thapa K B, Prasad R, et al. General regression neural network and radial basis neural network for the estimation of crop variables of lady finger[J]. J of the Indian Society of Remote Sensing, 2012, 40(4): 709-715.
  • 5Bansal A, Chen T T, Zhong S. Privacy preserving back-propagation neural network learning over arbitrarily partitioned data[J]. Neural Computing & Application, 2011, 20(1): 143-150.
  • 6Bashirov A E, Belaghi M J S. On application of euler’s differential method to a continued fraction depending on parameter[J]. Indian J of Pure and Applied Mathematics, 2014, 45(3): 285-295.
  • 7Manickavelu D, Vaidyanathan R U. Particle swarm optimization(PSO)-based node and link lifetime prediction algorithm for route recovery in MANET[J]. EURASIP J on Wireless Communications and Networking, 2014, 2014(107): 1-10.
  • 8Sung W T, Chiang Y C. Improved particle swarm optimization algorithm for android medical care IOT using modified parameters[J]. J of Medical Systems, 2012, 36(6): 3755-3763.
  • 9Farzi S, Dastjerdi A B. Leaf constrained minimal spanning trees solved by modified quantum-behaved particle swarm optimization[J]. Artificial Intelligence Review, 2010, 34(1): 1-17.
  • 10Tian N, Lai C H. Parallel quantum-behaved particle swarm optimization[J]. Int J of Machine Learning and Cybernetics, 2014, 5(2): 309-318.

共引文献42

同被引文献47

引证文献4

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部