计算机科学 ›› 2024, Vol. 51 ›› Issue (4): 344-352.doi: 10.11896/jsjkx.230100048
赵淼1, 谢良1, 林文静1, 徐海蛟2
ZHAO Miao1, XIE Liang1, LIN Wenjing1, XU Haijiao2
摘要: 近年来,投资组合管理问题在人工智能领域得到了广泛的研究,但现有的基于深度学习的量化交易方法还存在一些问题。首先,对股票的预测模式单一,通常一个模型只能训练出一个交易专家,交易决策也仅根据模型预测结果作出;其次,模型使用的数据源相对单一,只考虑了股票自身数据,忽略了整个市场风险对股票的影响。针对上述问题,提出了基于动态选择预测器的强化学习模型(DSDRL)。该模型分为3部分,首先提取股票数据的特征并传入多个预测器中,针对不同的投资策略训练多个预测模型,用动态选择器得到当前最优预测结果;其次,利用市场环境评价模块对当前市场风险进行量化,得到合适的投资金额比例;最后,在前两个模块的基础上建立了一种深度强化学习模型模拟真实的交易环境,基于预测的结果和投资金额比例得到实际投资组合策略。文中使用中证500和标普500的日k线数据进行测试验证,结果表明,此模型在夏普率等指标上均优于其他参照模型。
中图分类号:
[1]QIN Y,SONG D,CHEN H,et al.A dual-stage attention-based recurrent neural network for time series prediction[J].arXiv:1704.02971,2017. [2]XIE C,RAJAN D,CHAI Q.An interpretable Neural FuzzyHammerstein-Wiener network for stock price prediction[J].Information Sciences,2021,577:324-335. [3]TAKEUCHI L,LEE Y Y.Applying deep learning to enhance momentum trading strategies in stocks[R].Technical Report.Stanford,CA,USA:Stanford University,2013. [4]RUNDO F.Deep LSTM with reinforcement learning layer forfinancial trend prediction in FX high frequency trading systems[J].Applied Sciences,2019,9(20):4460. [5]SEZER O B,OZBAYOGLU A M.Algorithmic Financial Tra-ding with Deep Convolutional Neural Networks:Time Series to Image Conversion Approach[J].Applied Soft Computing,2018,70:525-538. [6]YANG H,LIU X Y,ZHONG S,et al.Deep reinforcement lear-ning for automated stock trading:an ensemble strategy[C]//Proceedings of the first ACM International Conference on AI in Finance.2020:1-8. [7]LIN H,ZHOU D,LIU W,et al.Learning multiple stock trading patterns with temporal routing adaptor and optimal transport[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.2021:1017-1026. [8]MILLER C,ARJUNAN P,KATHIRGAMANATHAN A,et al.The ASHRAE great energy predictor III competition:Overview and results[J].Science and Technology for the Built Environment,2020,26(10):1427-1447. [9]LIANG Y,KE S,ZHANG J,et al.Geoman:Multi-level attention networks for geo-sensory time series prediction[C]//IJCAI.2018:3428-3434. [10]GILBERT K.An ARIMA supply chain model[J].Management Science,2005,51(2):305-310. [11]DURBIN J,KOOPMAN S J.Time series analysis by state space methods[M].OUP Oxford,2012. [12]CAETANO M A L,YONEYAMA T.Characterizing abruptchanges in the stock prices using a wavelet decomposition me-thod[J].Physica A:Statistical Mechanics and its Applications,2007,383(2):519-526. [13]DING Q,WU S,SUN H,et al.Hierarchical Multi-Scale Gaus-sian Transformer for Stock Movement Prediction[C]//IJCAI.2020:4640-4646. [14]KVAMME H,SELLEREITE N,AAS K,et al.Predicting mortgage default using convolutional neural networks[J].Expert Systems with Applications,2018,102:207-217. [15]CHEN W,YEO C K,LAU C T,et al.Leveraging social media news to predict stock index movement using RNN-boost[J].Data & Knowledge Engineering,2018,118:14-24. [16]PIAO G,BRESLIN J G.Financial aspect and sentiment predictions with deep neural networks:an ensemble approach[C]//Companion Proceedings of the The Web Conference 2018.2018:1973-1977. [17]SPILAK B.Deep neural networks for cryptocurrencies price prediction[D].Berlin:Humboldt-Universität zu Berlin,2018. [18]SI W,LI J,DING P,et al.A multi-objective deep reinforcement learning approach for stock index future's intraday trading[C]//2017 10th International Symposium on Computational Intelligence and Design(ISCID).IEEE,2017:431-436. [19]GLASSERMAN P,KRSTOVSKI K,LALIBERTE P,et al.Choosing news topics to explain stock market returns[C]//Proceedings of the First ACM International Conference on AI in Finance.2020:1-8. [20]BRAHIMI B,TOUAHRIA M,TARI A.Improving sentimentanalysis in Arabic:A combined approach[J].Journal of King Saud University-Computer and Information Sciences,2021,33(10):1242-1250. [21]AZHIKODAN A R,BHAT A G K,JADHAV M V.Stocktrading bot using deep reinforcement learning[C]//Innovations in Computer Science and Engineering:Proceedings of the Fifth ICICSE 2017.Singapore:Springer,2019:41-49. [22]GRACE A.Can deep learning techniques improve the risk adjusted returns from enhanced indexing investment strategies[J/OL].https://arrow.tudublin.ie/cgi/viewcontent.cgi?article=1129&context=scschcomdis. [23]FU X Y,DU J H,GUO Y F,et al.A machine learning framework for stock selection[J].arXiv:1806.01743,2018. [24]CHEN L,GAO Q.Application of deep reinforcement learning on automated stock trading[C]//2019 IEEE 10th International Conference on Software Engineering and Service Science(ICSESS).IEEE,2019:29-33. [25]PUN C S,WANG L,WONG H Y.Financial thought experiment:a gan-based ap-proach to vast robust portfolio selection[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence(IJCAI'20).2020:451-458. [26]NEUNEIER R.Optimal asset allocation using adaptive dynamic programming[J].Advances in Neural Information Processing Systems,1995,8:952-958. [27]MOODY J,SAFFELL M.Reinforcement learning for trading[J].Advances in Neural Information Processing Systems,1998,11:917-923. [28]DENG Y,BAO F,KONG Y,et al.Deep direct reinforcement learning for financial signal representation and trading[J]. IEEE transactions on Neural Networks and Learning Systems,2016,28(3):653-664. [29]YU P,LEE J S,KULYATIN I,et al.Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization[J].ar-Xiv:1901.08740,2019. [30]LIU X Y,YANG H Y,CHEN Q,et al.Finrl:A deep reinforcement learning library forautomated stock trading in quantitative finance[J].arXiv:2011.09607,2020. [31]WANG Z C,HUANG B W,TU S,et al.Deeptrader:a deep reinforcement learning approach for risk-return balanced portfolio management with market conditions embedding[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2021:643-650. |
|