摘要
本文提出一种基于多路循环神经网络与深度学习的股票预测方法。针对股票的涨跌预测问题,使用分布式向量表示方法提取出股票相关的新闻文本特征,同时考虑到股票相关信息的时序性以及新闻影响的持续性特质,使用多路循环神经网络模型对所提取的特征与交易信息进行协同训练,从而获得历史信息的低维向量表示。最后将多个循环神经网络的输出进行拼接,利用深度神经网络共同对股票的涨跌进行分类预测。本文使用上证A股的价格与新闻数据进行实验,实验结果表明,本文所提出的方法在股票预测任务上具有明显的优越性。
A stock prediction method based on multiple recurrent neural network and deep learning is proposed in this paper.Aiming at predicting the rise and fall of stocks,the method in this paper extracts the features of news corpus information by distributed vector representation methods.Considering the natural of time-series stock related information and the persistence of news impact,multiple recurrent neural networks are used to collaborate process the features and stock trading information to obtain the history information embedding.Finally,the outputs of all recurrent neural networks are concatenated together to predict a stock.The data of Shanghai A-share market stock are used to do case study,which indicates that our method significantly outperforms the other baselines.
引文
[1] ADAM K,MARCET A,NICOLINI J P.Stock market volatility and learning[J].The Journal of Finance,2016,71:33-82.DOI:10.1111/jofi.12364.
[2] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-44.DOI:10.1038/nature14539.
[3] SI Y W,YIN J.OBST-based segmentation approach to financial time series[J].Engineering Applications of Artificial Intelligence,2013,26(10):2581-2596.DOI:10.1016/j.engappai.2013.08.015.
[4] FAMA E F.The Behaviour of stock market prices[J].Journal of Business,1965,38(1):34-105.DOI:10.1086/294743.
[5] XIE H,BIAN J, WANG M,et al.Is technical analysis informative in UK stock market?Evidence from decomposition-based vector autoregressive(DVAR)model[J].Journal of Systems Science and Complexity,2014,27(1):144-156.DOI:10.1007/s11424-014-3280-9.
[6] LI L L,LENG S,YANG J,et al.Stock market autoregressive dynamics:A multinational comparative study with quantile regression[J].Mathematical Problems in Engineering,2016(1):1-15.DOI:10.1155/2016/1285768.
[7] RUIZ E J,HRISTIDIS V,CASTILLO C,et al.Correlating financial time series with micro-blogging activity[C]//Proceedings of the fifth ACM international conference on Web search and data mining.New York:ACM,2012:513-522.DOI:10.1145/2124295.2124358.
[8] BRACHMAN R J,KHABAZA T,KLOESGEN W,et al.Mining business databases[J].Communications of the ACM,1996,39(11):42-48.DOI:10.1145/240455.240468.
[9] HARRIS Z S.Distributional structure[J].Word,1954,10(2-3):146-162.DOI:10.1080/00437956.1954.11659520.
[10] BHLER K.Sprachtheorie:Theory of language[M].Oxford,England:Fischer,1934.
[11] SOWA J F.Semantic networks[EB/OL].(2015-03-02)[2018-10-14].http://www.jfsowa.com/pubs/semnet.htm.
[12] CHOMSKY N.Three models for the description of language[J].IRE,Transactions on Information Theory,1956,2(3):112-124.DOI:10.1109/TIT.1956.1056813.
[13] CAMBRIA E.An introduction to concept-level sentiment analysis[C]//Mexican International Conference on Artificial Intelligence.Berlin:Springer,2013:478-483.DOI:10.1007/978-3-642-45111-9_41.
[14] RILOFF E,SHEPHERD J.A corpus-based approach for building semantic lexicons[EB/OL].(1997-06-10)[2018-10-14].https://arXiv.org/abs/cmp-lg/9706013.
[15] SUN R,ZHANG Y,ZHANG M,et al.Event-driven headline generation[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Stroudsburg:ACL,2015:462-472.
[16] DING X,ZHANG Y,LIU T,et al.Deep learning for event-driven stock prediction[C]//International Conference on Artificial Intelligence.Argentina:AAAI,2015:2327-2333.
[17] MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[J].Advances in Neural Information Processing Systems,2013:3111-3119.
[18] PENNINGTON J,SOCHER R,MANNING C D.Glove:Global vectors for word representation[C]//Proceedings of the 2014Conference on Empirical Methods in Natural Language Processing(EMNLP).Stroudsburg:ACL,2014:1532-1543.
[19] JOULIN A,GRAVE E,BOJANOWSKI P,et al.Bag of tricks for efficient text classification[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics:Volume 2,Short Papers.Stroudsburg:ACL,2017:427-431.
[20] SCHUSTER M,PALIWAL K P.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681.DOI:10.1109/78.650093.
[21] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[22] ZHANG L,AGGARWAL C,QI G.Stock price prediction via discovering multi-frequency trading patterns[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2017:2141-2149.
[23]GAO Q.Stock market forecasting using recurrent neural network[D].Columbia:University of MissouriColumbia,2016.
[24] RATHER A M,AGARWAL A,SASTRY V N.Recurrent neural network and a hybrid model for prediction of stock returns[J].Expert Systems with Applications,2015,42(6):3234-3241.
[25] ALTHELAYA K A,El-ALFY E M,MOHAMMED S.Evaluation of bidirectional LSTM for short-and long-term stock market prediction[C]//2018 9th International Conference on Information and Communication Systems(ICICS),[S.l.:s.n.],2018:151-156.
[26] ZHANG Z,CHEN W,YAN H.Stock prediction:a method based on extraction of news features and recurrent neural networks[EB/OL].(2017-07-19)[2018-10-14].https://arXiv.org/abs/1707.07585v1.
[27] OLAH C.Understanding LSTM networks[EB/OL].(2015-08-27)[2018-10-14].http://colah.github.io/posts/2015-08-Understanding-LSTMs/.
[28] KINGMA D P,BA L J.Adam:A method for stochastic optimization[EB/OL].(2014-12-22)[2018-10-14].https://arXiv.org/abs/1412.6980v1.
[29] ABADI M,AGARWAL A,BARHAM P,et al.Tensorflow:Large-scale machine learning on heterogeneous distributed systems[EB/OL].(2016-03-14)[2018-10-14].https://arXiv.org/abs/1603.04467v1.
[30] KIM Y.Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP).Stroudsburg:ACL,2014:1746-1751.