
Multi-Step-Ahead Crude Oil Price Forecasting Based on Hybrid Model
Zhenpeng TANG, Tingting ZHANG, Junchuan WU, Xiaoxu DU, Kaijie CHEN
China Journal of Econometrics ›› 2021, Vol. 1 ›› Issue (2) : 346-361.
Multi-Step-Ahead Crude Oil Price Forecasting Based on Hybrid Model
Accurately predicting the crude oil prices is vital for governors to make policies and essential for market participants to make investment decisions. We propose a hybrid multi-step-ahead forecasting model that integrates the secondary decomposition algorithm which combines variational modal decomposition (VMD) and integrated empirical modal decomposition (EEMD), differential evolution (DE) and extreme learning machine (ELM), namely, VMD-RES.-EEMD-DE-ELM, for more accurate crude oil price forecasting in this paper. To illustrate the superiority of the proposed model, the sample data of Brent and West Texas Intermediate (WTI) are used to validate the performance of the proposed model. The empirical results confirm that the proposed model achieves better performance compared to several other benchmark models in terms of forecasting accuracy and stability.
crude oil price / secondary decomposition / extreme learning machine {{custom_keyword}} /
表1 非组合预测模型对Brent原油和WTI原油现货价格的向前1步、3步和5步的预测结果 |
模型 | Brent | WTI | |||||
1步 | |||||||
ELM | 2.1348 | 1.7348 | 0.0277 | 1.8868 | 1.4684 | 0.0257 | |
KELM | 2.0601 | 1.6841 | 0.0269 | 1.8481 | 1.4452 | 0.0253 | |
DE-ELM | 2.0563 | 1.6894 | 0.0269 | 1.8475 | 1.4431 | 0.0252 | |
Brent | WTI | ||||||
3步 | |||||||
ELM | 2.1653 | 1.7691 | 0.0283 | 1.9850 | 1.5414 | 0.0270 | |
KELM | 2.1454 | 1.7497 | 0.0279 | 1.9321 | 1.5096 | 0.0264 | |
DE-ELM | 2.1333 | 1.7415 | 0.0279 | 1.9312 | 1.4982 | 0.0263 | |
Brent | WTI | ||||||
5步 | |||||||
ELM | 2.1841 | 1.8076 | 0.0288 | 1.9357 | 1.5199 | 0.0267 | |
KELM | 2.1533 | 1.7701 | 0.0283 | 1.9265 | 1.5089 | 0.0264 | |
DE-ELM | 2.1342 | 1.7606 | 0.0281 | 1.9137 | 1.5159 | 0.0266 |
注: |
表2 不考虑残差项分解的组合模型对Brent原油和WTI原油现货价格的向前1步、3步和5步的预测结果 |
模型 | Brent | WTI | |||||
1步 | |||||||
EEMD-DE-ELM | 1.2889 | 1.0451 | 0.0168 | 1.1414 | 0.8925 | 0.0157 | |
EEMD-VMD-DE-ELM | 0.4322 | 0.3534 | 0.0057 | 0.3651 | 0.2853 | 0.0049 | |
VMD-DE-ELM | 0.4820 | 0.3940 | 0.0063 | 0.4540 | 0.3593 | 0.0062 | |
Brent | WTI | ||||||
3步 | |||||||
EEMD-DE-ELM | 1.6750 | 1.3806 | 0.0223 | 1.5664 | 1.2456 | 0.0217 | |
EEMD-VMD-DE-ELM | 0.7949 | 0.6067 | 0.0098 | 0.7681 | 0.5978 | 0.0103 | |
VMD-DE-ELM | 0.5493 | 0.4389 | 0.0070 | 0.5222 | 0.4111 | 0.0071 | |
Brent | WTI | ||||||
5步 | |||||||
EEMD-DE-ELM | 1.8813 | 1.5437 | 0.0249 | 1.7380 | 1.3710 | 0.0238 | |
EEMD-VMD-DE-ELM | 1.1116 | 0.8809 | 0.0142 | 0.9769 | 0.7654 | 0.0133 | |
VMD-DE-ELM | 0.6622 | 0.5317 | 0.0086 | 0.5954 | 0.4657 | 0.0081 |
注: |
表3 考虑残差项的组合模型对Brent原油和WTI原油现货价格的向前1步、3步和5步的预测结果 |
模型 | Brent | WTI | |||||
1步 | |||||||
VMD-RES.-DE-ELM | 0.4599 | 0.3732 | 0.0059 | 0.4381 | 0.3485 | 0.0060 | |
VMD-RES.-EEMD-DE-ELM | 0.3146 | 0.2449 | 0.0039 | 0.2772 | 0.2186 | 0.0038 | |
Brent | WTI | ||||||
3步 | |||||||
VMD-RES.-DE-ELM | 0.5583 | 0.4476 | 0.0071 | 0.4880 | 0.3831 | 0.0067 | |
VMD-RES.-EEMD-DE-ELM | 0.4610 | 0.3745 | 0.0060 | 0.4106 | 0.3317 | 0.0057 | |
Brent | WTI | ||||||
5步 | |||||||
VMD-RES.-DE-ELM | 0.6641 | 0.5307 | 0.0086 | 0.5712 | 0.4449 | 0.0077 | |
VMD-RES.-EEMD-DE-ELM | 0.5838 | 0.4575 | 0.0074 | 0.5297 | 0.4154 | 0.0072 |
注: |
范秋枫, 王涛, 张智峰, 量子粒子群智能算法在国际布伦特原油价格预测中的应用[J]. 模糊系统与数学, 2017, 31 (4): 84- 90.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
李洪海, 石油价格走势及对石油上市公司的影响[J]. 管理世界, 2000, (6): 196- 197.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
任泽平, 能源价格波动对中国物价水平的潜在与实际影响[J]. 经济研究, 2012, 47 (8): 59- 69.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
田利辉, 谭德凯, 原油价格的影响因素分析: 金融投机还是中国需求?[J]. 经济学(季刊), 2015, 14 (3): 961- 982.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
王珏, 胡蓝艺, 齐琛, 基于网络关注度的大宗商品市场预测研究[J]. 系统工程理论与实践, 2017, 37 (5): 1163- 1171.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
杨云飞, 鲍玉昆, 胡忠义, 张瑞, 基于EMD和SVMs的原油价格预测方法[J]. 管理学报, 2010, 7 (12): 1884- 1889.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
张金良, 李德智, 谭忠富, 基于混合模型的国际原油价格预测研究[J]. 北京理工大学学报(社会科学版), 2019, 21 (1): 59- 64.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Bin H G, Zhu Q Y, Siew C K, (2004). Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks[C]//IEEE International Conference on Neural Networks-Conference Proceedings, 2: 985-990.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Contreras J, Espínola R, Nogales F J, Conejo J A, (2003). ARIMA Models to Predict Next-day Electricity Prices[C]//IEEE Transactions on Power Systems, 18(3): 1014-1020.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Qin A K, Huang V L, Suganthan P N, (2009). Differential Evolution Algorithm with Strategy Adaptation for Global Numerical Optimization[C]//IEEE Transactions on Evolutionary Computation, 13(2): 398-417.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |