TY - JOUR
T1 - A novel multiscale nonlinear ensemble leaning paradigm for carbon price forecasting
AU - Zhu, Bangzhu
AU - Ye, Shunxin
AU - Wang, Ping
AU - He, Kaijian
AU - Zhang, Tao
AU - Wei, Yi Ming
N1 - Publisher Copyright:
© 2018 Elsevier B.V.
PY - 2018/2
Y1 - 2018/2
N2 - In this study, a novel multiscale nonlinear ensemble leaning paradigm incorporating empirical mode decomposition (EMD) and least square support vector machine (LSSVM) with kernel function prototype is proposed for carbon price forecasting. The EMD algorithm is used to decompose the carbon price into simple intrinsic mode functions (IMFs) and one residue, which are identified as the components of high frequency, low frequency and trend by using the Lempel-Ziv complexity algorithm. The Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model is used to forecast the high frequency IMFs with ARCH effects. The LSSVM model with kernel function prototype is employed to forecast the high frequency IMFs without ARCH effects, the low frequency and trend components. The forecasting values of all the components are aggregated into the ones of original carbon price by the LSSVM with kernel function prototype-based nonlinear ensemble approach. Furthermore, particle swarm optimization is used for model selections of the LSSVM with kernel function prototype. Taking the popular prediction methods as benchmarks, the empirical analysis demonstrates that the proposed model can achieve higher level and directional predictions and higher robustness. The findings show that the proposed model seems an advanced approach for predicting the high nonstationary, nonlinear and irregular carbon price.
AB - In this study, a novel multiscale nonlinear ensemble leaning paradigm incorporating empirical mode decomposition (EMD) and least square support vector machine (LSSVM) with kernel function prototype is proposed for carbon price forecasting. The EMD algorithm is used to decompose the carbon price into simple intrinsic mode functions (IMFs) and one residue, which are identified as the components of high frequency, low frequency and trend by using the Lempel-Ziv complexity algorithm. The Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model is used to forecast the high frequency IMFs with ARCH effects. The LSSVM model with kernel function prototype is employed to forecast the high frequency IMFs without ARCH effects, the low frequency and trend components. The forecasting values of all the components are aggregated into the ones of original carbon price by the LSSVM with kernel function prototype-based nonlinear ensemble approach. Furthermore, particle swarm optimization is used for model selections of the LSSVM with kernel function prototype. Taking the popular prediction methods as benchmarks, the empirical analysis demonstrates that the proposed model can achieve higher level and directional predictions and higher robustness. The findings show that the proposed model seems an advanced approach for predicting the high nonstationary, nonlinear and irregular carbon price.
KW - Carbon price forecasting
KW - Empirical mode decomposition
KW - Kernel function prototype
KW - Least squares support vector machine
KW - Particle swarm optimization
UR - http://www.scopus.com/inward/record.url?scp=85044365547&partnerID=8YFLogxK
U2 - 10.1016/j.eneco.2017.12.030
DO - 10.1016/j.eneco.2017.12.030
M3 - Article
AN - SCOPUS:85044365547
SN - 0140-9883
VL - 70
SP - 143
EP - 157
JO - Energy Economics
JF - Energy Economics
ER -