Forcasting of energy futures market and synchronization based on stochastic gated recurrent unit model

被引：30
作者：
Li, Jingmiao [1 ]
Wang, Jun [1 ]
机构：
[1] Beijing Jiaotong Univ, Sch Sci, Beijing 100044, Peoples R China
来源：
ENERGY | 2020年 / 213卷
基金：
中国国家自然科学基金;
关键词：
Energy market; Prediction neural network for energy; futures; Gated recurrent unit; Stochastic time intensity; Prediction accuracy estimate; Composite multiscale cross-sample entropy; FINANCIAL TIME-SERIES; SHORT-TERM LOAD; ARTIFICIAL NEURAL-NETWORKS; NATURAL-GAS CONSUMPTION; OIL PRICE PREDICTION; FORECASTING-MODEL; MEMORY; GENERATION; DEMAND;
D O I：
10.1016/j.energy.2020.118787
中图分类号：
O414.1 [热力学];
学科分类号：
摘要：
Energy futures market has occupied an extremely significant position in financial markets, attracting a large amount of scholars to search out its price formation mechanism. To predict the price of energy futures has become a pivotal issue. For the sake of enhancing the forecasting accuracy of energy futures prices, a novel model ST-GRU is proposed by embedding stochastic time intensity function into gated recurrent unit model (GRU). ST-GRU, GRU, LSTM, WNN and BPNN models are applied to predict the daily closing prices of West Texas Intermediate crude oil, Brent crude oil, Natural gas and Heating oil respectively. In error assessment, the prediction effects of various models are compared by general benchmarks. Then composite multiscale cross-sample entropy (CMSCE) algorithm is utilized to analyze the synchronization between the predicted value and the real value. In order to further predict the volatility of futures closing price and demonstrate the superiority of the ST-GRU model, the abovementioned five models are used to predict and analyze 5-day, 10-day and 20-day moving average logarithmic return (MALR) series of four energy indexes. Finally, comparative experiments indicate that ST-GRU model has the highest prediction precision and the best learning performance. (C) 2020 Elsevier Ltd. All rights reserved.
引用
收藏
页数：17
相关论文
共 59 条
[1]   Big data analysis for brain tumor detection: Deep convolutional neural networks [J].
Amin, Javeria ;
Sharif, Muhammad ;
Yasmin, Mussarat ;
Fernandes, Steven Lawrence .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2018, 87 :290-297
[2]   Financial time series forecasting model based on CEEMDAN and LSTM [J].
Cao, Jian ;
Li, Zhi ;
Li, Jian .
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2019, 519 :127-139
[3]   Crude oil price prediction model with long short term memory deep learning based on prior knowledge data transfer [J].
Cen, Zhongpei ;
Wang, Jun .
ENERGY, 2019, 169 :160-171
[4]   Gated recurrent neural network with sentimental relations for sentiment classification [J].
Chen, Chaotao ;
Zhuo, Run ;
Ren, Jiangtao .
INFORMATION SCIENCES, 2019, 502 :268-278
[5]   A gated recurrent unit neural networks based wind speed error correction model for short-term wind power forecasting [J].
Ding, Min ;
Zhou, Hao ;
Xie, Hua ;
Wu, Min ;
Nakanishi, Yosuke ;
Yokoyama, Ryuichi .
NEUROCOMPUTING, 2019, 365 :54-61
[6]   A novel decompose-ensemble methodology with AIC-ANN approach for crude oil forecasting [J].
Ding, Yishan .
ENERGY, 2018, 154 :328-336
[7]   Application of artificial neural networks for testing long-term energy policy targets [J].
Dozic, Damir J. ;
Urosevic, Branka D. Gvozdenac .
ENERGY, 2019, 174 :488-496
[8]   Energy price prediction based on independent component analysis and gated recurrent unit neural network [J].
E, Jianwei ;
Ye, Jimin ;
He, Lulu ;
Jin, Haihong .
ENERGY, 2019, 189
[9]   Assessment of deep recurrent neural network-based strategies for short-term building energy predictions [J].
Fan, Cheng ;
Wang, Jiayuan ;
Gang, Wenjie ;
Li, Shenghan .
APPLIED ENERGY, 2019, 236 :700-710
[10]   Long short-term memory-based recurrent neural networks for nonlinear target tracking [J].
Gao, Chang ;
Yan, Junkun ;
Zhou, Shenghua ;
Chen, Bo ;
Liu, Hongwei .
SIGNAL PROCESSING, 2019, 164 :67-73
123456