广西师范大学学报（自然科学版） ›› 2021, Vol. 39 ›› Issue (2): 41-50.doi: 10.16088/j.issn.1001-6600.2020080201

• CCIR2020 • 上一篇    下一篇

基于经验模态分解和多分支LSTM网络汇率预测

薛涛, 丘森辉*, 陆豪, 秦兴盛   

  1. 广西师范大学 电子工程学院, 广西 桂林 541004
  • 收稿日期:2020-08-02 修回日期:2020-10-02 出版日期:2021-03-25 发布日期:2021-04-15
  • 通讯作者: 丘森辉(1988—),男,广西贵港人,广西师范大学讲师。E-mail:qiusenhui@gxnu.edu.cn
  • 基金资助:
    国家自然科学基金(61976063)

Exchange Rate Prediction Based on Empirical Mode Decomposition and Multi-branch LSTM Network

XUE Tao, QIU Senhui *, LU Hao, QIN Xingsheng   

  1. School of Electronic Engineering, Guangxi Normal University, Guilin Guangxi 541004, China
  • Received:2020-08-02 Revised:2020-10-02 Online:2021-03-25 Published:2021-04-15

PDF (PC)

428

摘要： 作为一种新型信号变换算法,经验模态分解(empirical mode decomposition, EMD)能够解决傅里叶变换等方法受限于特定基函数的缺陷。本文针对人工神经网络对高频金融时间序列预测准确率不足的问题,结合EMD和韦布尔分布对金融时间序列进行预处理,提出一种基于经验模态分解和多分支长短期记忆网络的分类预测模型,用于从高频金融时间序列中提取有关价格走势的信息并对未来的价格运动趋势做出预测。通过对2009—2012年欧元兑美元汇率时间序列进行预测,实验结果表明,所提出的网络模型可以得到较高的预测准确率和计算速度,并且同普通LSTM网络相比,提高了泛化能力和模型稳定性。

关键词: LSTM网络, 金融时间序列, 汇率预测, 分类模型, 经验模态分解, 深度学习

Abstract: As a new signal transformation algorithm, Empirical Mode Decomposition (EMD) can solve the limitation of some existing methods such as Fourier transform that are limited to specific basis functions. Aiming at the problem of insufficient prediction accuracy of artificial neural networks for high-frequency financial time series, this paper combines EMD and Weibull distribution to preprocess financial time series. A classification model based on EMD and multi-branch long short-term memory network is proposed in this paper. The multi-branch LSTM network based on EMD is used to extract information about price movements from high-frequency financial time series and make predictions about future price movements. By predicting the FX time series of EURUSD from 2009 to 2012, the experimental results show that the proposed model can obtain higher prediction accuracy and calculation speed. Compared with ordinary LSTM network, the generalization ability and model stability are improved.

Key words: LSTM network, financial time series, FX predicting, classification model, empirical mode decomposition, deep learning

中图分类号: 

  • TP183
[1] 黄丽明,陈维政,闫宏飞,等.基于循环神经网络和深度学习的股票预测方法[J].广西师范大学学报(自然科学版),2019,37(1):13-22.DOI: 10.16088/j.issn.1001-6600.2019.01.002.
[2] SANGVINATSOS A.A random walk down wall street:the time-tested strategy for successful investing[J].Quantitative Finance,2017,17(3):327-330.DOI: 10.1080/14697688.2016.1256598.
[3] FARIAS NAZÁRIO R T,E SILVA J L,SOBREIRO V A,et al.A literature review of technical analysis on stock markets[J].The Quarterly Review of Economics and Finance,2017,66:115-126.DOI: 10.1016/j.qref.2017.01.014.
[4] LIU J X,SUN T N,LUO Y L,et al.An echo state network architecture based on quantum logic gate and Its optimization[J].Neurocomputing,2020,371:100-107.DOI: 10.1016/j.neucom.2019.09.002.
[5] CAO J,LI Z,LI J.Financial time series forecasting model based on CEEMDAN and LSTM[J].Physica A:Statistical Mechanics and Its Applications,2019,519:127-139.DOI: 10.1016/j.physa.2018.11.061.
[6] 李晓光,宋宝燕,张昕.基于滑动多窗口的时间序列流趋势变化检测[J].电子学报,2010,38(2):321-326.
[7] 章登义,欧阳黜霏,吴文李.针对时间序列多步预测的聚类隐马尔科夫模型[J].电子学报,2014,42(12):2359-2364.DOI: 10.3969/j.issn.0372-2112.2014.12.004.
[8] YU Y W,WANG S S,ZHANG L J.Stock price forecasting based on BP neural network model of network public opinion[C]//2017 2nd International Conference on Image,Vision and Computing.Piscataway,NJ:IEEE Press,2017:1058-1062.DOI: 10.1109/ICIVC.2017.7984716.
[9] 吕凯晨,闫宏飞,陈翀.基于沪深300成分股的量化投资策略研究[J].广西师范大学学报(自然科学版),2019,37(1):1-12.DOI: 10.16088/j.issn.1001-6600.2019.01.001.
[10] OLIVEIRA N,CORTEZ P,AREAL N.The impact of microblogging data for stock market prediction:using twitter to predict returns,volatility,trading volume and survey sentiment indices[J].Expert Systems with Applications,2017,73:125-144.DOI: 10.1016/j.eswa.2016.12.036.
[11] 李艳红,贾丽娜,王素格,等.基于动态窗口的微博突发话题检测方法[J].计算机应用与软件,2020,37(5):30-37.DOI: 10.3969/j.issn.1000-386x.2020.05.006.
[12] TROIANO L,VILLA E M,LOIA V.Replicating a trading strategy by means of LSTM for financial industry applications[J].IEEE Transactions on Industrial Informatics,2018,14(7):3226-3234.DOI: 10.1109/TII.2018.2811377.
[13] BIONDO A E,PLUCHINO A,RAPISARDA A,et al.Are random trading strategies more successful than technical ones?[J].PLoS ONE,2013,8(7):e68344.DOI: 10.1371/journal.pone.0068344.
[14] DENG Y,BAO F,KONG Y Y,et al.Deep direct reinforcement learning for financial signal representation and trading[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(3):653-664.DOI: 10.1109/TNNLS.2016.2522401.
[15] GREFF K,SRIVASTAVA R K,KOUTNÍK J,et al.LSTM:a search space odyssey[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(10):2222-2232.DOI: 10.1109/TNNLS.2016.2582924.
[16] LIU J X,ZHANG J L,LUO Y L,et al.Mass spectral substance detections using long short-term memory networks[J].IEEE Access,2019,7:10734-10744.DOI: 10.1109/ACCESS.2019.2891548.
[17] FISCHER T,KRAUSS C.Deep learning with long short-term memory networks for financial market predictions[J].European Journal of Operational Research,2018,270(2):654-669.DOI: 10.1016/j.ejor.2017.11.054.
[18] CHANG X J,YU Y L,YANG Y,et al.Semantic pooling for complex event analysis in untrimmed videos[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(8):1617-1632.DOI: 10.1109/TPAMI.2016.2608901.
[19] PALANGI H,DENG L,SHEN Y L,et al.Deep sentence embedding using long short-term memory networks:analysis and application to information retrieval[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2016,24(4):694-707.DOI: 10.1109/TASLP.2016.2520371.
[20] ALLEN F,KARJALAINEN R.Using genetic algorithms to find technical trading rules[J].Journal of Financial Economics,1999,51(2):245-271.DOI: 10.1016/S0304-405X(98)00052-X.
[21] PATEL J,SHAH S,THAKKAR P.Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques[J].Expert Systems with Applications,2015,42(1):259-268.DOI: 10.1016/j.eswa.2014.07.040.
[22] DIXON M,KLABJAN D,BANG J H.Classification-based financial markets prediction using deep neural networks[J].Algorithmic Finance,2017,6(3/4):67-77.DOI: 10.3233/AF-170176.
[23] ARÉVALO A,NIÁO J,HERNÁNDEZ G,et al.High-frequency trading strategy based on deep neural networks[C]//InternationIntelligent Computing Methodologies:12th International Conference,ICIC 2016,Lanzhou,China,August 2-5,2016,Proceedings,Part III.Berlin:Springer,2016:424-436.DOI: 10.1007/978-3-319-42297-8_40.
[24] CAI X G,HU S,LIN X L.Feature extraction using restricted Boltzmann machine for stock price prediction[C]//2012 IEEE International Conference on Computer Science and Automation Engineering:Volume 3.Piscataway,NJ:IEEE Press,2012:80-83.DOI: 10.1109/CSAE.2012.6272913.
[25] CHEN K,ZHOU Y,DAI F Y.A LSTM-based method for stock returns prediction:a case study of China stock market[C]//2015 IEEE International Conference on Big Data.Piscataway,NJ:IEEE Press,2015:2823-2824.DOI: 10.1109/BigData.2015.7364089.
[26] 张金磊,罗玉玲,付强.基于门控循环单元神经网络的金融时间序列预测[J].广西师范大学学报(自然科学版),2019,37(2):82-89.DOI: 10.16088/j.issn.1001-6600.2019.02.010.
[27] LIN C S,CHIU S H,LIN T Y.Empirical mode decomposition-based least squares support vector regression for foreign exchange rate forecasting[J].Economic Modelling,2012,29(6):2583-2590.DOI: 10.1016/j.econmod.2012.07.018.
[28] SEZER O B,GUDELEK M U,OZBAYOGLU A M.Financial time series forecasting with deep learning:a systematic literature review:2005-2019[J].Applied Soft Computing,2020,90:106181.DOI: 10.1016/j.asoc.2020.106181.
[29] LIU J X,SUN T N,LUO Y L,et al.Financial data forecasting using optimized echo state network[C]//Neural Information Processing:25th International Conference,ICONIP 2018,Siem Reap,Cambodia,December 13-16,2018,Proceedings,Part V.Berlin:Springer,2018:138-149.DOI: 10.1007/978-3-030-04221-9_13.
[1] 杨州, 范意兴, 朱小飞, 郭嘉丰, 王越. 神经信息检索模型建模因素综述[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 1-12.
[2] 邓文轩, 杨航, 靳婷. 基于注意力机制的图像分类降维方法[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 32-40.
[3] 唐熔钗, 伍锡如. 基于改进YOLO-V3网络的百香果实时检测[J]. 广西师范大学学报（自然科学版）, 2020, 38(6): 32-39.
[4] 张明宇, 赵猛, 蔡夫鸿, 梁钰, 王鑫红. 基于深度学习的波浪能发电功率预测[J]. 广西师范大学学报（自然科学版）, 2020, 38(3): 25-32.
[5] 李维勇, 柳斌, 张伟, 陈云芳. 一种基于深度学习的中文生成式自动摘要方法[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 51-63.
[6] 刘英璇, 伍锡如, 雪刚刚. 基于深度学习的道路交通标志多目标实时检测[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 96-106.
[7] 张金磊, 罗玉玲, 付强. 基于门控循环单元神经网络的金融时间序列预测[J]. 广西师范大学学报（自然科学版）, 2019, 37(2): 82-89.
[8] 黄丽明, 陈维政, 闫宏飞, 陈翀. 基于循环神经网络和深度学习的股票预测方法[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 13-22.
[9] 岳天驰, 张绍武, 杨亮, 林鸿飞, 于凯. 基于两阶段注意力机制的立场检测方法[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 42-49.
[10] 余传明, 李浩男, 安璐. 基于多任务深度学习的文本情感原因分析[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 50-61.
[11] 王祺, 邱家辉, 阮彤, 高大启, 高炬. 基于循环胶囊网络的临床语义关系识别研究[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 80-88.
[12] 胡维平, 董振华. EMD的单次分解频域属性及IMF的生成机理研究[J]. 广西师范大学学报（自然科学版）, 2012, 30(3): 94-99.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 胡锦铭, 韦笃取. 分数阶永磁同步电机的广义同步研究[J]. 广西师范大学学报（自然科学版）, 2020, 38(6): 14 -20 .
[2] 朱勇建, 罗坚, 秦运柏, 秦国峰, 唐楚柳. 基于光度立体和级数展开法的金属表面缺陷检测方法[J]. 广西师范大学学报（自然科学版）, 2020, 38(6): 21 -31 .
[3] 杨丽婷, 刘学聪, 范鹏来, 周岐海. 中国非人灵长类声音通讯研究进展[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 1 -9 .
[4] 宾石玉, 廖芳, 杜雪松, 许艺兰, 王鑫, 武霞, 林勇. 罗非鱼耐寒性能研究进展[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 10 -16 .
[5] 刘静, 边迅. 直翅目昆虫线粒体基因组的特征及应用[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 17 -28 .
[6] 李兴康, 钟恩主, 崔春艳, 周佳, 李小平, 管振华. 西黑冠长臂猿滇西亚种鸣叫行为监测[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 29 -37 .
[7] 和鑫明, 夏万才, 巴桑, 龙晓斌, 赖建东, 杨婵, 王凡, 黎大勇. 滇金丝猴主雄应对配偶雌性数量的理毛策略[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 38 -44 .
[8] 付文, 任宝平, 林建忠, 栾科, 王朋程, 王宾, 黎大勇, 周岐海. 济源太行山猕猴种群数量和保护现状[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 45 -52 .
[9] 郑景金, 梁霁鹏, 张克处, 黄爱面, 陆倩, 李友邦, 黄中豪. 基于木本植物优势度的白头叶猴食物选择研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 53 -64 .
[10] 杨婵, 万雅琼, 黄小富, 袁旭东, 周洪艳, 方浩存, 黎大勇, 李佳琦. 基于红外相机技术的小麂(Muntiacus reevesi)活动节律[J]. 广西师范大学学报（自然科学版）, 2021, 39(1): 65 -70 .
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发