Stock price prediction based on hybrid preprocessing neural network model

LI Jianlei; SHI Weikang

doi:10.11714/acta.snus.ZR20240010

您当前的位置：

首页 >

文章列表页 >

Stock price prediction based on hybrid preprocessing neural network model

更新时间：2026-03-06

- Stock price prediction based on hybrid preprocessing neural network model
- Acta Scientiarum Naturalium Universitatis Sunyatseni Pages: 1-9(2026)
- 作者机构：
  
  华北水利水电大学数学与统计学院，河南郑州 450046
- 作者简介：
- 基金信息：
- DOI：10.11714/acta.snus.ZR20240010
  CLC： TP183
- Received：05 January 2024，
  
  Revised：2025-11-15，
  
  Accepted：15 November 2025，
  
  Online First：06 March 2026，
- 稿件说明：
移动端阅览
LI Jianlei, SHI Weikang. Stock price prediction based on hybrid preprocessing neural network model[J/OL]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2026, 1-9.
DOI：

LI Jianlei, SHI Weikang. Stock price prediction based on hybrid preprocessing neural network model[J/OL]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2026, 1-9. DOI： 10.11714/acta.snus.ZR20240010.

摘要

在股价预测领域，多元时间序列中通常存在多个变量之间的复杂相互关联，同时受到多种因素的影响，这增加了准确预测的难度. 为了应对这一挑战，提出了一种创新的混合预处理技术方法. 首先，利用经验小波变换（EWT）同时提取时间序列的低频和高频成分；接着，引入了动态时间规整（DTW）和差分动态时间规整（DDTW）来度量不同分量之间的相似性，从而有效地识别了股价时间序列中的关联模式和相似性.在进一步的分析中，采用滑动窗口处理高频分量，并进行主成分分析，同时对低频分量进行直接主成分分析. 最后，将这些方法应用于多个神经网络预测模型中，发现模型的性能和预测精度都有显著提升.

Abstract

In the field of stock price prediction， there often exists complex interrelationships among multiple variables in multivariate time series， simultaneously influenced by various factors， which increases the difficulty of accurate prediction. To address this challenge， we propose an innovative hybrid preprocessing technique. Firstly， we utilize Empirical Wavelet Transform （EWT） to simultaneously extract the low-frequency and high-frequency components of time series. Subsequently， we introduce Dynamic Time Warping （DTW） and Differential Dynamic Time Warping （DDTW） to measure the similarity between different components， effectively identifying correlated patterns and similarities in stock price time series. In further analysis， we employ a sliding window approach for high-frequency components and conduct Principal Component Analysis （PCA）， while directly applying PCA to low-frequency components. Finally， we apply these methods to multiple neural network prediction models and observe significant improvements in model performance and prediction accuracy.

关键词

Keywords

references

崔明建，孙元章，柯德平，等， 2014 . 基于原子稀疏分解理论的短期风电功率滑动预测［J］. 电力自动化设备， 34 （ 1 ）： 120 - 127 .

李海林，梁叶，王少春， 2018 . 时间序列数据挖掘中的动态时间弯曲研究综述［J］. 控制与决策， 33 （ 8 ）： 1345 - 1353 .

王东庆，周建华，伏云发， 2023 . EWT算法在单通道脑电信号眼电伪迹自动去除中的研究［J］. 电子测量与仪器学报， 37 （ 2 ）： 121 - 129 .

AMPOUNTOLAS A ， 2019 . Forecasting hotel demand uncertainty using time series Bayesian VAR models ［J］. Tour Econ ， 25 （ 5 ）： 734 - 756 .

ANDREESKI C ， MECHKAROSKA D ， 2020 . Modelling， forecasting and testing decisions for seasonal time series in tourism ［J］. Acta Polytech Hung ， 17 （ 10 ）： 149 - 171 .

CHEONG C W ， 2009 . Modeling and forecasting crude oil markets using ARCH-type models ［J］. Energy Policy ， 37 （ 6 ）： 2346 - 2355 .

DENG Y ， WANG B F ， LU Z M ， 2020 . A hybrid model based on data preprocessing strategy and error correction system for wind speed forecasting ［J］. Energy Convers Manag ， 212 ： 112779 .

EDIGER V Ş ， AKAR S ， 2007 . ARIMA forecasting of primary energy demand by fuel in Turkey ［J］. Energy Policy ， 35 （ 3 ）： 1701 - 1708 .

EGRIOGLU E ， BAS E ， 2023 . A new hybrid recurrent artificial neural network for time series forecasting ［J］. Neural Comput Appl ， 35 ： 2855 - 2865 .

FARID A B ， FATHY E M ， SHARAF ELDIN A ， et al ， 2021 . Software defect prediction using hybrid model （CBIL） of convolutional neural network （CNN） and bidirectional long short-term memory （Bi-LSTM）［J］. PeerJ Comput Sci ， 7 ： e739 .

FIJANI E ， BARZEGAR R ， DEO R ， et al ， 2019 . Design and implementation of a hybrid model based on two-layer decomposition method coupled with extreme learning machines to support real-time environmental monitoring of water quality parameters ［J］. Sci Total Environ ， 648 ： 839 - 853 .

GARCIA R C ， CONTRERAS J ， van AKKEREN M ， et al ， 2005 . A GARCH forecasting model to predict day-ahead electricity prices ［J］. IEEE Trans Power Syst ， 20 （ 2 ）： 867 - 874 .

JAIN B J ， 2019 . Making the dynamic time warping distance warping-invariant ［J］. Pattern Recognit ， 94 ： 35 - 52 .

KRITHIKAIVASAN B ， ZENG Y ， DEKA K ， et al ， 2007 . ARCH-based traffic forecasting and dynamic bandwidth provisioning for periodically measured nonstationary traffic ［J］. IEEE/ACM Trans Netw ， 15 （ 3 ）： 683 - 696 .

KUMAR U ， JAIN V K ， 2010 . ARIMA forecasting of ambient air pollutants （O 3 ， NO， NO 2 and CO）［J］. Stoch Environ Res Risk Assess ， 24 （ 5 ）： 751 - 760 .

LEI C ， RAN L ， 2008 . Short-term wind speed forecasting model for wind farm based on wavelet decomposition ［C］// 2008 Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies ， 2008： 2525 - 2529 .

LI X H ， 2022 . Application of neural networks in financial time series forecasting models ［J］. J Funct Spaces ， 2022： 7817264 .

LIN L ， JIANG Y ， XIAO H L ， et al ， 2020 . Crude oil price forecasting based on a novel hybrid long memory GARCH-M and wavelet analysis model ［J］. Phys A Stat Mech Appl ， 543 ： 123532 .

LIU J ， TANG X H ， GUAN X ， 2023 . Grain protein function prediction based on self-attention mechanism and bidirectional LSTM ［J］. Brief Bioinform ， 24 （ 1 ）： bbac493 .

MI X W ， LIU H ， LI Y F ， 2019 . Wind speed prediction model using singular spectrum analysis， empirical mode decomposition and convolutional support vector machine ［J］. Energy Convers Manag ， 180 ： 196 - 205 .

NAIK J ， DASH S ， DASH P K ， et al ， 2018 . Short term wind power forecasting using hybrid variational mode decomposition and multi-kernel regularized pseudo inverse neural network ［J］. Renew Energy ， 118 ： 180 - 212 .

NEDAIVODA I V ， PRIMIN M A ， MASLENNIKOV Y V ， 2019 . Algorithm for analysis of magnetocardiac signals： The principal component method ［J］. J Commun Technol Electron ， 64 ： 1414 - 1421 .

PEGALAJAR M C ， RUIZ L G B ， 2022 . Time series forecasting for energy consumption ［J］. Energies ， 15 （ 3 ）： 773 .

QIAN Z ， PEI Y ， ZAREIPOUR H ， et al ， 2019 . A review and discussion of decomposition-based hybrid models for wind energy forecasting applications ［J］. Appl Energy ， 235 ： 939 - 953 .

QUILTY J ， ADAMOWSKI J ， 2018 . Addressing the incorrect usage of wavelet-based hydrological and water resources forecasting models for real-world applications with best practices and a new forecasting framework ［J］. J Hydrol ， 563 ： 336 - 353 .

WANG J Z ， QIN S S ， ZHOU Q P ， et al ， 2015 . Medium-term wind speeds forecasting utilizing hybrid models for three different sites in Xinjiang， China ［J］. Renew Energy ， 76 ： 91 - 101 .

WANG S X ， ZHANG N ， WU L ， et al ， 2016 . Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method ［J］. Renew Energy ， 94 ： 629 - 636 .

WIDIPUTRA H ， MAILANGKAY A ， GAUTAMA E ， 2021 . Multivariate CNN-LSTM model for multiple parallel financial time-series prediction ［J］. Complexity ， 2021 （ 1 ）： 9903518 .

XUE B ， HONG H ， ZHOU S Z ， et al ， 2019 . Morphological filtering enhanced empirical wavelet transform for mode decomposition ［J］. IEEE Access ， 7 ： 14283 - 14293 .

ZHANG L L ， LI M S ， JI T Y ， et al ， 2016 . Short-term wind power prediction based on intrinsic time-scale decomposition and LS-SVM ［C］// 2016 IEEE Innovative Smart Grid Technologies-Asia （ISGT-Asia）， 2016： 41 - 45 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Characteristics of agricultural water use in Emin irrigation area based on principal component and information entropy

An MPS algorithm accelerated by neural network on edge computing

Detail-aware discriminative feature learning model for vehicle re-identification

Sparse floating car data filling based on NB and DTW combined model

Development of high-efficiency gemini foaming agent ULT-1 for coalbed methane well

Related Author

LIU Yu

LI Shunshun

REN Congzhe

YANG Haimei

MA Junyong

FAN Wenbo

WANG Shiwei

JIANG Junyang

Related Institution

Xinjiang Academy of Agricultural Reclamation

Key Laboratory of Modern Water-Saving Irrigation of Xinjiang Production & Construction Group

College of Water Conservancy & Architectural Engineering， Shihezi University

School of Aeronautics and Astronautics， Sun Yat-sen University

Department of Robotics and Mechatronics， University of Twente

Postal code：510275
Tel：020-84112585，84113223 Email：xuebaozr@mail.sysu.edu.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰