A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting

被引：329
|
作者：
Smyl, Slawek [1 ]
机构：
[1] Uber Technol, 555 Market St, San Francisco, CA 94104 USA
来源：
INTERNATIONAL JOURNAL OF FORECASTING | 2020年 / 36卷 / 01期
关键词：
Forecasting competitions; M4; Dynamic computational graphs; Automatic differentiation; Long short term memory (LSTM) networks; Exponential smoothing; OF-THE-ART;
D O I：
10.1016/j.ijforecast.2019.03.017
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
This paper presents the winning submission of the M4 forecasting competition. The submission utilizes a dynamic computational graph neural network system that enables a standard exponential smoothing model to be mixed with advanced long short term memory networks into a common framework. The result is a hybrid and hierarchical forecasting method. (C) 2019 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码：75 / 85
页数：11
相关论文
共 50 条
  • [1] A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting (vol 36, pg 75, 2020)
    Smyl, Slawek
    [J]. INTERNATIONAL JOURNAL OF FORECASTING, 2021, 37 (03) : 1313 - 1313
  • [2] Hybrid Neural Networks for Time Series Forecasting
    Averkin, Alexey
    Yarushev, Sergey
    [J]. ARTIFICIAL INTELLIGENCE (RCAI 2018), 2018, 934 : 230 - 239
  • [3] Traffic Flow Forecasting Neural Networks Based on Exponential Smoothing Method
    Chan, K. Y.
    Dillon, T. S.
    Singh, J.
    Chang, E.
    [J]. 2011 6TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA), 2011, : 376 - 381
  • [4] Robust recurrent neural networks for time series forecasting
    Zhang, Xueli
    Zhong, Cankun
    Zhang, Jianjun
    Wang, Ting
    Ng, Wing W. Y.
    [J]. NEUROCOMPUTING, 2023, 526 : 143 - 157
  • [5] A new improved forecasting method integrated fuzzy time series with the exponential smoothing method
    Ge, Peng
    Wang, Jun
    Ren, Peiyu
    Gao, Huafeng
    Luo, Yuyan
    [J]. INTERNATIONAL JOURNAL OF ENVIRONMENT AND POLLUTION, 2013, 51 (3-4) : 206 - 221
  • [6] Automating simple exponential smoothing forecasting with a recurrent neural network
    Wu, SI
    [J]. SIXTH, SEVENTH, AND EIGHTH WORKSHOPS ON VIRTUAL INTELLIGENCE: ACADEMIC/INDUSTRIAL/NASA/DEFENSE TECHNICAL INTERCHANGE AND TUTORIALS, 1996, 2878 : 108 - 116
  • [7] Forecasting correlated time series with exponential smoothing models
    Corberan-Vallet, Ana
    Bermudez, Jose D.
    Vercher, Enriqueta
    [J]. INTERNATIONAL JOURNAL OF FORECASTING, 2011, 27 (02) : 252 - 265
  • [8] Ensembles of Recurrent Neural Networks for Robust Time Series Forecasting
    Krstanovic, Sascha
    Paulheim, Heiko
    [J]. ARTIFICIAL INTELLIGENCE XXXIV, AI 2017, 2017, 10630 : 34 - 46
  • [9] Time series forecasting by recurrent product unit neural networks
    F. Fernández-Navarro
    Maria Angeles de la Cruz
    P. A. Gutiérrez
    A. Castaño
    C. Hervás-Martínez
    [J]. Neural Computing and Applications, 2018, 29 : 779 - 791
  • [10] Time series forecasting by recurrent product unit neural networks
    Fernandez-Navarro, F.
    de la Cruz, Maria Angeles
    Gutierrez, P. A.
    Castano, A.
    Hervas-Martinez, C.
    [J]. NEURAL COMPUTING & APPLICATIONS, 2018, 29 (03): : 779 - 791
12345