Time Series Prediction Based on Decomposition and Synthesis
Authors: 
Junguang Li, Shuying YangAuthors Info & Claims
Junguang Li, Shuying YangAuthors Info & ClaimsPages 171 - 177
Abstract
In recent years, the deep learning method has been widely used in the financial field, promoting the development of stock price forecasting. The time series data in reality has complex characteristics, and the traditional single model has great limitations in prediction. For the problem that the time series data is too complicated, this paper proposes a time series mixed prediction model based on decomposition and synthesis. The time series is decomposed by empirical mode decomposition (EMD). For the problem that the calculation complexity becomes larger after decomposition, and the prediction error of each sub-component leads to the total error is still large. In this paper, the sampled entropy (SE) method is used to combine the decomposed subsequences, which reduces the computational complexity and total error of the algorithm. The combined sequence is predicted by the LSTM neural network. The experimental result show that the prediction accuracy of the model is significantly improved compared with the traditional model.
References
[1]
Akter S, Wamba S F. Big data and disaster management: a systematic review and agenda for future research[J]. Annals of Operations Research, 2017(9):1--21.
[2]
Chen K, Jiang J, Zheng F, et al. A novel data-driven approach for residential electricity consumption prediction based on ensemble learning[J]. Energy, 2018, 150:49--60.
[3]
Ni X Y, Huang H, Du W P. Relevance analysis and short-term prediction of PM2.5 concentrations in Beijing based on multi-source data[J]. Atmospheric Environment, 2017, 150:146--161.
[4]
Feldmann A, Anso J, Bell B, et al. Temperature Prediction Model for Bone Drilling Based on Density Distribution and In Vivo Experiments for Minimally Invasive Robotic Cochlear Implantation[J]. Annals of Biomedical Engineering, 2016, 44(5):1576--1586.
[5]
Xi C, Lei P, Zhang M, et al. A Public Traffic Demand Forecast Method Based on Computational Experiments[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(4):984--995.
[6]
Ruiz G, Marcos A F D. Evidence for criticality in financial data[J]. European Physical Journal B, 2018, 91(1):1.
[7]
Min Gan, Hui Peng, Xue-ping Dong. A hybrid algorithm to optimize RBF network architecture and parameters for nonlinear time series prediction[J]. Applied Mathematical Modelling,2012,36(7).
[8]
Yixuan Zhang, Ningbo Cui, Yu Feng, Daozhi Gong, Xiaotao Hu. Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China[J]. Computers and Electronics in Agriculture,2019,164.
[9]
LSTM network: a deep learning approach for short-term traffic forecast. Zhao Z, Chen W, Wu X, et al. let Intelligent Transport Systems. 2017
[10]
Reddy Bhargava K, Delen Dursun. Predicting hospital readmission for lupus patients: An RNN-LSTM-based deep-learning methodology.[J]. Computers in biology and medicine,2018,101.
[11]
F. Li and C. Liu, "Application Study of BP Neural Network on Stock Market Prediction," 2009 Ninth International Conference on Hybrid Intelligent Systems, Shenyang, 2009, pp. 174--178.
[12]
Yong Shuai, Tailiang Song, Jianping Wang.Integrated parallel forecasting model based on modified fuzzy time series and SVM[J].Journal of Systems Engineering and Electronics,2017,28(04):766--775.
[13]
R. Jeberson Retna Raj, T. Sasipraba, M. Vasudev, Sanjay Gupta, Md. Rizwan, Piyush srivastava. Predicting the Impact of Climate Change on Tidal Zone Fishes Using SVM Approach[J]. Procedia Computer Science,2016,92.
[14]
G.Peter Zhang. Time series forecasting using a hybrid ARIMA and neural network model[J]. Neurocomputing,2003,50.
[15]
Wang Long, Cheng Tianle, Chen Yu. Short-term load forecasting based on EMD and ELM [J]. Electric Power Science and Engineering, 2014, 30 (6): 54--58.
[16]
Liu H, Chen C, Tian H Q, et al. A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks[J]. Renewable Energy, 2012, 48(6):545--556.
[17]
Hochreiter, S, Schmidhuber, J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735--1780.
[18]
Yentes J M, Hunt N, Schmid K K, et al. The appropriate use of approximate entropy and sample entropy with short data sets[J]. Annals of Biomedical Engineering, 2013, 41(2):349--365.
[19]
Richman J S, Lake D E, Moorman J R. Sample entropy[J]. Methods in Enzymology, 2004.
Index Terms
- Time Series Prediction Based on Decomposition and Synthesis
Recommendations
Research on the prediction of short time series based on EMD-LSTM
An algorithm based on EMD-LSTM (Empirical Mode Decision – Long Short Term Memory) is proposed for predicting short time series with uncertainty, rapid changes, and no following cycle. First, the algorithm eliminates the abnormal data; second, the ...
A self-organizing modular neural network based on empirical mode decomposition with sliding window for time series prediction
AbstractTime series is mostly with a chaotic nature and non-stationary characteristic in real-word, which makes it difficult to be modeled and predicted accurately. To solve this problem, we introduce a novel self-organizing modular neural ...
Highlights- EMD is used to decompose time series based on time characteristic dynamically, which eliminates the drawback of some subnetworks with few training data and ...
Research on a hybrid prediction model for stock price based on long short-term memory and variational mode decomposition
AbstractThe stock market plays a vital role in the economic and social organization of many countries. Since stock price time series are highly noisy, nonparametric, volatility, complexity, nonlinearity, dynamics, and chaos, the stock market prediction is ...
Comments
Information & Contributors
Information
Published In
December 2019
614 pages
ISBN:9781450372619
DOI:10.1145/3377713
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- Chinese Univ. of Hong Kong: Chinese University of Hong Kong
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 07 February 2020
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ACAI 2019
ACAI 2019: 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence
December 20 - 22, 2019
Sanya, China
Acceptance Rates
ACAI '19 Paper Acceptance Rate 97 of 203 submissions, 48%;
Overall Acceptance Rate 173 of 395 submissions, 44%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 139Total Downloads
- Downloads (Last 12 months)4
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Sep 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in