An Adaptive Hybrid Learning Paradigm Integrating CEEMD, ARIMA and SBL for Crude Oil Price Forecasting

Jiang Wu, Yu Chen, Tengfei Zhou and Taiyong Li
Additional contact information
Jiang Wu: School of Economic Information Engineering, Southwestern University of Finance and Economics, Chengdu 611130, China
Yu Chen: School of Economic Information Engineering, Southwestern University of Finance and Economics, Chengdu 611130, China
Tengfei Zhou: School of Economic Information Engineering, Southwestern University of Finance and Economics, Chengdu 611130, China
Taiyong Li: School of Economic Information Engineering, Southwestern University of Finance and Economics, Chengdu 611130, China

Energies, 2019, vol. 12, issue 7, 1-23

Abstract: Crude oil is one of the main energy sources and its prices have gained increasing attention due to its important role in the world economy. Accurate prediction of crude oil prices is an important issue not only for ordinary investors, but also for the whole society. To achieve the accurate prediction of nonstationary and nonlinear crude oil price time series, an adaptive hybrid ensemble learning paradigm integrating complementary ensemble empirical mode decomposition (CEEMD), autoregressive integrated moving average (ARIMA) and sparse Bayesian learning (SBL), namely CEEMD-ARIMA&SBL-SBL (CEEMD-A&S-SBL), is developed in this study. Firstly, the decomposition method CEEMD, which can reduce the end effects and mode mixing, was employed to decompose the original crude oil price time series into intrinsic mode functions ( IMF s) and one residue. Then, ARIMA and SBL with combined kernels were applied to predict target values for the residue and each single IMF independently. Finally, the predicted values of the above two models for each component were adaptively selected based on the training precision, and then aggregated as the final forecasting results using SBL without kernel-tricks. Experiments were conducted on the crude oil spot prices of the West Texas Intermediate (WTI) and Brent crude oil to evaluate the performance of the proposed CEEMD-A&S-SBL. The experimental results demonstrated that, compared with some state-of-the-art prediction models, CEEMD-A&S-SBL can significantly improve the prediction accuracy of crude oil prices in terms of the root mean squared error (RMSE), the mean absolute percent error (MAPE), and the directional statistic (Dstat).

Keywords: crude oil price forecasting; time series forecasting; hybrid model; complementary ensemble empirical mode decomposition (CEEMD); sparse Bayesian learning (SBL) (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
https://www.mdpi.com/1996-1073/12/7/1239/pdf (application/pdf)
https://www.mdpi.com/1996-1073/12/7/1239/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:12:y:2019:i:7:p:1239-:d:218826

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().