Forecasting global crude oil price fluctuation by novel hybrid E-STERNN model and EMCCS assessment
- PDF / 2,742,417 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 12 Downloads / 197 Views
METHODOLOGIES AND APPLICATION
Forecasting global crude oil price fluctuation by novel hybrid E-STERNN model and EMCCS assessment Lihong Zhang1 · Jun Wang1
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Energy futures are a very significant part of commodity futures, no less than the influence of the spot market. A novel hybrid neural network (denote by E-STERNN) is proposed through combining Elman recurrent neural network model with stochastic time strength (ST-ERNN), and ensemble empirical mode decomposition (EEMD) is also introduced to improve the performance of forecasting neural network system for energy markets. ST-ERNN model is established for taking into account the weight of energy historical data with time variations. EEMD is an algorithm that decomposes any non-stationary and nonlinear time series into simple and independent time sequence. From the empirical research for four global energy market prices, the proposed hybrid E-STERNN model is verified to have higher prediction accuracy compared with the original ERNN and the ST-ERNN models. Moreover, a new error evaluation approach, called the exponent of multi-scale composite complexity synchronization (EMCCS), is utilized to analyze and estimate the prediction performance, and the demonstration analyses confirm that the hybrid E-STERNN model has higher prediction accuracy for global energy futures indexes. Keywords Forecasting hybrid neural network · Stochastic time strength · Ensemble empirical mode decomposition · Crude oil price series · Multi-scale composite complexity synchronization
Abbreviations ERNN Elman recurrent neural network ST-ERNN Elman recurrent neural network model with stochastic time strength EEMD Ensemble empirical mode decomposition EMD Empirical mode decomposition ANN Artificial neural network IMF Intrinsic mode functions WTI West Texas Intermediate crude oil Brent Brent crude oil PTR (NYSE) PetroChina Co. Ltd. CEO (NYSE) China National Offshore Oil Co. Ltd. MCCS Multi-scale composite complexity synchronization CID Complexity invariant distance Communicated by V. Loia.
B B 1
Lihong Zhang [email protected] Jun Wang [email protected] School of Science, Beijing Jiaotong University, Beijing 100044, China
1 Introduction In the coming decades, oil will still be an irreplaceable energy source as the blood of modern industry, affecting the development direction of the entire world economy. Oil is an indispensable energy for economic growth and development (Quayyoum et al. 2019; Roman et al. 2018). China is the world’s largest oil importer, and West Texas Intermediate Crude Oil (WTI) and Brent Crude Oil (Brent) are regarded as the benchmark of global crude oil pricing. Futures trading on the Intercontinental Exchange of London and the New York Mercantile Exchange are benchmark oil prices in the market (Niu and Wang 2014; Wang and Li 2018; Zavadska et al. 2018). Crude oil has an enormous contradiction between supply and demand, high price volatility and complex price formation factors as the most essentia
Data Loading...
