Title: A support vector machine-based ensemble prediction for crude oil price with VECM and STEPMRS

Authors: Dongkuan Xu; Tianjia Chen; Wei Xu

Addresses: School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China; School of Information, Renmin University of China, Beijing 100872, China ' School of Statistics, Renmin University of China, Beijing 100872, China ' School of Information, Renmin University of China, Beijing 100872, China

Abstract: Crude oil price prediction attracts more and more attentions, not only for its importance to the modern industry, but also for its complex price movement. This paper proposes a support vector machine-based ensemble model to forecast crude oil price based on VECM and Stochastic Time Effective Pattern Modelling and Recognition System (STEPMRS). In the proposed model, VECM is first used to model the trend of crude oil price, and then STEPMRS is offered to forecast errors. Finally, SVM is employed to integrate the results from the ones of VECM and STEPMRS to make the final forecasting values more accurate and desirable. The WTI spot price and a set of financial indicators are utilised as inputs for the validation purpose. The empirical results show that the proposed ensemble model can significantly improve the forecasting performance, compared with other 11 models in four aspects, and be an alternative tool to predict crude oil price.

Keywords: crude oil prices; price forecasting; price prediction; STEPMRS; VECM; SVM; support vector machines; spot prices; financial indicators.

DOI: 10.1504/IJGEI.2015.069488

International Journal of Global Energy Issues, 2015 Vol.38 No.1/2/3, pp.18 - 48

Available online: 18 May 2015 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article