[1]王子玥,谢维波,李斌.变步长BLSTM集成学习股票预测[J].华侨大学学报(自然科学版),2019,40(2):269-276.[doi:10.11830/ISSN.1000-5013.201807050]
 WANG Ziyue,XIE Weibo,LI Bin.Variable Step BLSTM Ensemble Learning for Stock Prediction[J].Journal of Huaqiao University(Natural Science),2019,40(2):269-276.[doi:10.11830/ISSN.1000-5013.201807050]
点击复制

变步长BLSTM集成学习股票预测()
分享到:

《华侨大学学报(自然科学版)》[ISSN:1000-5013/CN:35-1079/N]

卷:
第40卷
期数:
2019年第2期
页码:
269-276
栏目:
出版日期:
2019-03-20

文章信息/Info

Title:
Variable Step BLSTM Ensemble Learning for Stock Prediction
文章编号:
1000-5013(2019)02-0269-08
作者:
王子玥 谢维波 李斌
华侨大学 计算机科学与技术学院, 福建 厦门 361021
Author(s):
WANG Ziyue XIE Weibo LI Bin
College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China
关键词:
双向长短期记忆网络 集成学习 变步长 股票价格 改进均方误差损失
Keywords:
bi-directional long short-term memory ensemble learning variable step stock price improved mean-square error loss
分类号:
TP183
DOI:
10.11830/ISSN.1000-5013.201807050
文献标志码:
A
摘要:
提出采用变步长双向长短期记忆网络(BLSTM)集成学习方法学习历史数据中股票价格变动的规律.针对股票涨跌变化的预测改进均方误差(MSE)损失函数,采用简易的模拟交易盈利评价指标以更好地度量预测模型在金融市场中的期望表现.通过前10~50步长的数据训练BLSTM,预测下1 min各股票的涨跌变化.实验结果验证了不同数据预处理下,改进损失函数的有效性及变步长集成方法相对于单一网络的有效性.
Abstract:
We present a bi-directional long short-term memory(BLSTM)ensemble learning method with variable step to learn regular pattern of stock price fluctuate from history data. Improved the mean-square error(MSE)loss function for stock fluctuation prediction. This paper use simple simulated trading strategy as evaluating indicator to better evaluate the model performance in financial markets. Use the step between 10 and 50 to train BLSTM to forecast the rise and fall of the stock in next minute. The experimental results verified the effectiveness of the BLSTM ensemble learning method under different data preprocessing and variable step ensemble is more effective than any single network.

参考文献/References:

[1] MALKIEL B G,FAMA E F.Efficient capital markets: A review of theory and empirical work[J].Journal of Finance,1970,25(2):383-417.DOI:10.2307/2325486.
[2] 杜威望,肖曙光.FF五因子模型在中国股票市场的改进研究[J].华侨大学学报(哲学社会科学版),2018(3):39-53.DOI:10.16067/j.cnki.35-1049/c.2018.03.004.
[3] KIM K J.Financial time series forecasting using support vector machines[J].Neurocomputing,2003,55(1/2):307-319.DOI:10.1016/S0925-2312(03)00372-2.
[4] SOMANI P,TALELE S,SAWANT S.Stock market prediction using Hidden Markov Model[C]//IEEE 7th Joint International Information Technology and Artificial Intelligence Conference.Chongqing:IEEE Press,2014:89-92.DOI:10.1109/ITAIC.2014.7065011.
[5] CHEN Kai,ZHOU Yi,DAI Fangyan.A LSTM-based method for stock returns prediction: A case study of China stock market[C]//IEEE International Conference on Big Data.Santa Clara:IEEE Press,2015:2823-2824.DOI:10.1109/BigData.2015.7364089.
[6] DI PERSIO L,HONCHAR O.Artificial neural networks architectures for stock price prediction: Comparisons and applications[J].International Journal of Circuits, Systems and Signal Processing,2016,10:403-413.
[7] YANG Bing,GONG Zijia,YANG Wenqi.Stock market index prediction using deep neural network ensemble[C]//36th Chinese Control Conference.Dalian:IEEE Press,2017:3882-3887.DOI:10.23919/ChiCC.2017.8027964.
[8] BAO Wei,YUE Jun,RAO Yulei.A deep learning framework for financial time series using stacked autoencoders and long-short term memory[J].Plos One,2017,12(7):e0180944.DOI:10.6084/m9.figshare.5028110.
[9] ZHONG Weiping,ZHANG Lili.The prediction research of safety stock based on the combinatorial forecasting model[C]//Proceedings of the 2015 International Conference on Computational Science and Engineering.Paris:Atlantis Press,2015:200-206.
[10] ZHANG Xiangzhou,HU Yong,XIE Kang,et al.A causal feature selection algorithm for stock prediction modeling[J].Neurocomputing,2014,142:48-59.DOI:10.1016/j.neucom.2014.01.057.
[11] AKITA R,YOSHIHARA A,MATSUBARA T,et al.Deep learning for stock prediction using numerical and textual information[C]//IEEE/ACIS 15th International Conference on Computer and Information Science.Okayama:IEEE Press,2016:1-6.DOI:10.1109/ICIS.2016.7550882.
[12] DING Xiao,ZHANG Yue,LIU Ting,et al.Deep learning for event-driven stock prediction[C]//International Conference on Artificial Intelligence.Buenos Aires:AAAI Press,2015:2327-2333.DOI:10.1109/ICALIP.2010.56851 87.
[13] MEZHAR A,RAMDANI M,EIMZABI A.Exploiting noisy data normalization for stock market prediction[J].Journal of Engineering and Applied Sciences,2017,12(1):69-77.DOI:10.3923/jeasci.2017.69.77.
[14] NELSON D M Q,PEREIRA A C M,DE OLIVEIRA R A.Stock market’s price movement prediction with LSTM neural networks[C]//International Joint Conference on Neural Networks.Anchorage:IEEE Press,2017:1419-1426.
[15] SCHUSTER M,PALIWAL K K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681.DOI:10.1109/78.650093.
[16] EYRAUD-LOISEL A.Backward stochastic differential equations with enlarged filtration: Option hedging of an insider trader in a financial market with jumps[J].Stochastic Processes and Their Applications,2005,115(11):1745-1763.DOI:10.1016/j.spa.2005.05.006.
[17] ZHUGE Qun,XU Lingyu,ZHANG Gaowei.LSTM neural network with emotional analysis for prediction of stock price[J].Engineering Letters,2017,25(2):167-175.
[18] SINGH R,SRIVASTAVA S.Stock prediction using deep learning[J].Multimedia Tools and Applications,2017,76(18):18569-18584.DOI:10.1007/s11042-016-4159-7.
[19] FISCHER T,KRAUSS C.Deep learning with long short-term memory networks for financial market predictions[J].Fau Discussion Papers in Economics,2017,270(2):1-32.DOI:10.1016/j.ejor.2017.11.054.
[20] LAVRENKO V,SCHMILL M,LAWRIE D,et al.Mining of concurrent text and time series[C]//Proceedings of the KDD 2000 Conference Text Mining Workshop.Doha:[s.n.],2000:37-44.DOI:10.1017/CBO9781107415324.004.

相似文献/References:

[1]范慧琳.机器学习的若干方法分析[J].华侨大学学报(自然科学版),1995,16(1):116.[doi:10.11830/ISSN.1000-5013.1995.01.0116]
 Fan Huilin.An Analysis of Several Methods of Machine Learning[J].Journal of Huaqiao University(Natural Science),1995,16(2):116.[doi:10.11830/ISSN.1000-5013.1995.01.0116]
[2]洪铭,汪鸿翔,刘晓芳,等.采用负相关学习的SVM集成算法[J].华侨大学学报(自然科学版),2018,39(6):942.[doi:10.11830/ISSN.1000-5013.201611103]
 HONG Ming,WANG Hongxiang,LIU Xiaofang,et al.SVM Ensembles Algorithm Using Negative Correlation Learning[J].Journal of Huaqiao University(Natural Science),2018,39(2):942.[doi:10.11830/ISSN.1000-5013.201611103]
[3]李威宏,童昕,李占福,等.集成学习在直线振动筛的应用及参数优化[J].华侨大学学报(自然科学版),2020,41(6):695.[doi:10.11830/ISSN.1000-5013.201912026]
 LI Weihong,TONG Xin,LI Zhanfu,et al.Application and Parameter Optimization of Ensemble Learning in Linear Vibrating Screen[J].Journal of Huaqiao University(Natural Science),2020,41(2):695.[doi:10.11830/ISSN.1000-5013.201912026]

备注/Memo

备注/Memo:
收稿日期: 2018-07-29
通信作者: 谢维波(1964-),男,教授,博士,主要从事信号处理、视频图像分析的研究.E-mail:xwblxf@hqu.edu.cn.
基金项目: 国家自然科学基金资助项目(61271383); 华侨大学研究生科研创新能力培育计划项目(1611314016)
更新日期/Last Update: 2019-03-20