计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 39-45.doi: 10.11896/jsjkx.210600124

• 智能计算 • 上一篇    下一篇

基于LSTM混合模型的比特币价格预测

张宁, 方靖雯, 赵雨宣   

  1. 中央财经大学金融学院 北京100081
  • 出版日期:2021-11-10 发布日期:2021-11-12
  • 通讯作者: 方靖雯(stb16fjw@126.com)
  • 作者简介:nzhang@amss.ac.cn
  • 基金资助:
    中央高校基本科研业务费专项基金;中央财经大学新兴交叉学科建设项目

Bitcoin Price Forecast Based on Mixed LSTM Model

ZHANG Ning, FANG Jing-wen, ZHAO Yu-xuan   

  1. School of Finance,Central University of Finance and Economics,Beijing 100081,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:ZHANG Ning,born in 1978,Ph.D,professor.His main research interests include fintech and artificial intelligence.
    FANG Jing-wen,born in 1999,master.Her main research interests include sequence forecasting and so on.
  • Supported by:
    Fundamental Research Funds for the Central Universities and Emerging Interdisciplinary Construction Project of Central University of Finance and Economics.

摘要: 聚焦于具有极度非线性、非平稳性等特征的比特币价格预测问题,在长短时记忆网络(Long Short-Term Memory,LSTM)基础上构建了4个混合预测模型,利用小波变换(Wavelet Transform,WT)以及自适应噪声的完备经验模态分解(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise,CEEMDAN)对序列进行分解与重构,并引入了样本熵(Sample Entropy,SE)进行重构优化,使用LSTM对重构以后的子序列分别进行预测,最后将其叠加得到最终的预测结果。在预测结果的评判上,使用均方根误、平均绝对百分误以及希尔不等系数来进行拟合评价,并将结果与单一LSTM模型进行比较。研究发现混合模型的预测准确性均优于单一模型,且样本熵的引入可有效降低预测误差。

关键词: 比特币价格, 长短时记忆网络, 小波变换, 自适应噪声完备经验模态分解, 样本熵

Abstract: For the reason that Bitcoin price is highly nonlinear and non-stationary,this paper proposes four mixed forecasting model based on Long Short-Term Memory (LSTM) model to get better prediction performance.Firstly,we use Wavelet Transform (WT) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to decompose and reconstruct the original sequence.Then,we introduce Sample Entropy (SE) to optimize the reconstruction.Finally,we predict the reconstructed sub-sequences respectively using LSTM and superpose the outcomes yields of prediction results.To evaluate the prediction performance,three evaluation functions are used,which are RMSE,MAPE and TIC.Besides,the results are compared with single LSTM model prediction result.The research shows that the prediction accuracy of mixed model is better than that of the single model,and the introduction of Sample Entropy can effectively reduce prediction error.

Key words: Bitcoin price, Long short-term memory network, Wavelet transform, Complete ensemble empirical mode decomposition with adaptive noise, Sample entropy

中图分类号: 

  • TP183
[1]DONALDSON R G,KAMSTRA M.Neural network forecastcombining with interactioneffects[J].Journal of the Franklin Institute,1999,336(2):227-236.
[2]TAKEUCHI L,LEE Y Y A.Applying deep learning to enhance momentum trading strategies in stocks[R].Technical Report,Stanford University,2013.
[3]WU W,CHEN W Q,LIU B.Prediction of ups and downs ofstock market by BP neural networks [J].Journal of Dalian University of Technology,2001,41(1):9-15.
[4]SONGX Y,CHEN N S.Financial prediction system based oncombination of genetic algorithm with BP neural network [J].Journal of Shanghai Jiao Tong University,2016,50(2):313-316.
[5]SUTSKEVER I,VINYALS O,LE Q V.Sequence to sequencelearning with neural networks[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2.2014:3104-3112.
[6]GRAVES A,JAITLY N.Towards end-to-end speech recogni-tion with recurrent neural networks[C]//International Confe-rence on Machine Learning.PMLR,2014:1764-1772.
[7] ROONDIWALA M,PATEL H,VARMA S.Predicting stockprices using LSTM[J].International Journal of Science and Research,2017,6(4):1754-1756.
[8] BAO W,YUE J,RAO Y.A deep learning framework for financial time series using stacked autoencoders and long-short term memory[J].PloS one,2017,12(7):e0180944.
[9] SHAH D,ZHANG K.Bayesian regression and Bitcoin[C]//2014 52nd annual Allerton conference on communication,control,and computing (Allerton).IEEE,2014:409-414.
[10]YANG S Y,KIM J.Bitcoin Market Return and Volatility Forecasting Using Transaction Network Flow Properties[C]// 2015 IEEE Symposium Series on Computational Intelligence (SSCI).IEEE,2015.
[11] MCNALLY S,ROCHE J,CATON S.Predicting the price of bitcoin using machine learning[C]//2018 26th Euromicro International Conference on Parallel,Distributed and Network-based Processing (PDP).IEEE,2018:339-343.
[12]STENQVIST E,LÖNNÖ J.Predicting Bitcoin price fluctuation with Twitter sentiment analysis[EB/OL].(2017-06-16) [2018-01-13].http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-209191.
[13]RAVI C.Fuzzy Crow Search Algorithm-Based Deep LSTM for Bitcoin Prediction[J].International Journal of Distributed Systems and Technologies (IJDST),2020,11(4):53-71.
[14]ZHANG X,LAI K K,WANG S Y.A new approach for crude oil price analysis based on empirical mode decomposition[J].Energy Economics,2008,30(3):905-918.
[15]TORRES M E,COLOMINAS M A,SCHLOTTHAUER G,et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2011:4144-4147.
[1] 罗婷瑞, 贾建, 张瑞. 基于可调Q因子小波变换和迁移学习的癫痫脑电信号检测[J]. 计算机科学, 2020, 47(7): 199-205.
[2] 刘云,尹传环,胡迪,赵田,梁宇. 基于循环神经网络的通信卫星故障检测[J]. 计算机科学, 2020, 47(2): 227-232.
[3] 文豪, 陈昊. 基于LSTM循环神经网络的税收预测[J]. 计算机科学, 2020, 47(11A): 437-443.
[4] 王启发, 王中卿, 李寿山, 周国栋. 基于交叉注意力机制和新闻正文的评论情感分类[J]. 计算机科学, 2020, 47(10): 222-227.
[5] 张阳峰, 韦仕鸿, 邓娜娜, 王文瑞. 基于小波降噪的振动传感器数据分析[J]. 计算机科学, 2019, 46(6A): 537-539.
[6] 刘佳慧, 王昱洁, 雷艺. 基于LSTM的CSI手势识别方法[J]. 计算机科学, 2019, 46(11A): 283-288.
[7] 高忠石, 苏旸, 柳玉东. 基于PCA-LSTM的入侵检测研究[J]. 计算机科学, 2019, 46(11A): 473-476.
[8] 王倩, 于来行, 曹彦, 张磊, 秦杰, 叶海琴. 基于Fibonacci置乱的小波域数字图像盲水印算法[J]. 计算机科学, 2018, 45(6): 135-140.
[9] 司念文,王衡军,李伟,单义栋,谢鹏程. 基于注意力长短时记忆网络的中文词性标注模型[J]. 计算机科学, 2018, 45(4): 66-70.
[10] 杨艳春,李娇,党建武,王阳萍. 基于冗余小波变换与引导滤波的多聚焦图像融合[J]. 计算机科学, 2018, 45(2): 301-305.
[11] 翟奥博,温显斌,张鑫. 基于改进双树复小波和灰度-梯度共生矩阵的纹理图像检索算法[J]. 计算机科学, 2017, 44(6): 274-277.
[12] 张正伟,吴礼发,严云洋. 基于多尺度分解与预测误差扩展的可逆图像水印算法[J]. 计算机科学, 2017, 44(12): 100-104.
[13] 魏雅娟,范九伦,任方. 基于混沌和小波变换的音频加密算法[J]. 计算机科学, 2017, 44(12): 94-99.
[14] 曹义亲,贺亚飞,黄晓生. 基于区域特性的压缩感知多聚焦融合算法[J]. 计算机科学, 2017, 44(1): 295-299.
[15] 楚建浦,何光辉,刘玉馨. 优化的小波变换和改进的LDA相融合的人脸识别算法[J]. 计算机科学, 2016, 43(Z11): 147-150.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 冯芙蓉, 张兆功. 目标轮廓检测技术新进展[J]. 计算机科学, 2021, 48(6A): 1 -9 .
[2] 孙正, 张小雪. 生物光声成像中声反射伪影抑制方法的研究进展[J]. 计算机科学, 2021, 48(6A): 10 -14 .
[3] 周欣, 刘硕迪, 潘薇, 陈媛媛. 自然交通场景中的车辆颜色识别[J]. 计算机科学, 2021, 48(6A): 15 -20 .
[4] 黄雪冰, 魏佳艺, 沈文宇, 凌力. 基于自适应加权重复值滤波和同态滤波的MR图像增强[J]. 计算机科学, 2021, 48(6A): 21 -27 .
[5] 江妍, 马瑜, 梁远哲, 王原, 李光昊, 马鼎. 基于分数阶麻雀搜索优化OTSU肺组织分割算法[J]. 计算机科学, 2021, 48(6A): 28 -32 .
[6] 冯霞, 胡志毅, 刘才华. 跨模态检索研究进展综述[J]. 计算机科学, 2021, 48(8): 13 -23 .
[7] 周文辉, 石敏, 朱登明, 周军. 基于残差注意力网络的地震数据超分辨率方法[J]. 计算机科学, 2021, 48(8): 24 -31 .
[8] 朝乐门, 尹显龙. 人工智能治理理论及系统的现状与趋势[J]. 计算机科学, 2021, 48(9): 1 -8 .
[9] 雷羽潇, 段玉聪. 面向跨模态隐私保护的AI治理法律技术化框架[J]. 计算机科学, 2021, 48(9): 9 -20 .
[10] 王俊, 王修来, 庞威, 赵鸿飞. 面向科技前瞻预测的大数据治理研究[J]. 计算机科学, 2021, 48(9): 36 -42 .