Improved EEMD-based crude oil price forecasting using LSTM networks

Considering the actual demand of crude oil price forecasting, a novel model based on ensemble empirical mode decomposition (EEMD) and long short-term memory (LSTM) is proposed. In practical work, the model trained by historical data will be used in later data. Then the forecasting models based on EEMD need re-execute EEMD to update decomposition results of price series after getting new data. In this process, the decomposition results of same period will not stay entirely identical, and even the number of decomposition results could change Unfortunately, in this case the traditional decomposition-ensemble models trained by historical data break down. To overcome this disadvantage, a method to select same number of proper inputs in different situations of decomposition results is developed. And for extracting feature from selected components more adequately, LSTM is introduced as forecasting method to predict price movement directly. For illustration and verification purposes, the proposed model is used to predict the crude oil spot price of West Texas Intermediate (WTI). Empirical results demonstrate that the proposed model still work well when the number of decomposition results varies, thus is promising for forecasting crude oil price.

[1]  Sam Mirmirani,et al.  A Comparison of VAR and Neural Networks with Genetic Algorithm in Forecasting Price of Oil , 2003, IC-AI.

[2]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[3]  Navdeep Jaitly,et al.  Towards End-To-End Speech Recognition with Recurrent Neural Networks , 2014, ICML.

[4]  Ling Tang,et al.  LSSVR ensemble learning with uncertain parameters for crude oil price forecasting , 2017, Appl. Soft Comput..

[5]  Ling Tang,et al.  A hybrid grid-GA-based LSSVR learning paradigm for crude oil price forecasting , 2016, Neural Computing and Applications.

[6]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[7]  Jianping Li,et al.  A deep learning ensemble approach for crude oil price forecasting , 2017 .

[8]  Ling Tang,et al.  A non-iterative decomposition-ensemble learning paradigm using RVFL network for crude oil price forecasting , 2017, Appl. Soft Comput..

[9]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[10]  Lean Yu,et al.  A randomized-algorithm-based decomposition-ensemble learning methodology for energy price forecasting , 2018, Energy.

[11]  M. A. Kaboudan,et al.  Compumetric forecasting of crude oil prices , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[12]  Ling Tang,et al.  Linear and nonlinear Granger causality investigation between carbon market and crude oil market: A multi-scale approach , 2015 .

[13]  Ling Tang,et al.  EEMD-LSSVR-Based Decomposition-and-Ensemble Methodology with Application to Nuclear Energy Consumption Forecasting , 2011, 2011 Fourth International Joint Conference on Computational Sciences and Optimization.

[14]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[15]  Xueyong Liu,et al.  The evolution of spillover effects between oil and stock markets across multi-scales using a wavelet-based GARCH–BEKK model , 2017 .

[16]  C. Aloui,et al.  Crude oil price forecasting: Experimental evidence from wavelet decomposition and neural network modeling , 2012 .

[17]  A. Lanza,et al.  Modeling and forecasting cointegrated relationships among heavy oil and product prices , 2005 .

[18]  Ekin Tokat,et al.  Forecasting oil price movements with crack spread futures , 2009 .

[19]  Hua Han,et al.  Bandwidth Empirical Mode Decomposition and its Application , 2008, Int. J. Wavelets Multiresolution Inf. Process..

[20]  Hubert Cardot,et al.  A new boosting algorithm for improved time-series forecasting with recurrent neural networks , 2008, Inf. Fusion.

[21]  Kin Keung Lai,et al.  Hybrid approaches based on LSSVR model for container throughput forecasting: A comparative study , 2013, Appl. Soft Comput..

[22]  Jiaqiu Wang,et al.  Local online kernel ridge regression for forecasting of urban travel times , 2014 .

[23]  Ai Jun Hou,et al.  A Nonparametric GARCH Model of Crude Oil Price Return Volatility , 2012 .

[24]  Ling Tang,et al.  Ensemble Forecasting for Complex Time Series Using Sparse Representation and Neural Networks , 2017 .

[25]  Norden E. Huang,et al.  Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method , 2009, Adv. Data Sci. Adapt. Anal..

[26]  Ling Tang,et al.  An EEMD-based multi-scale fuzzy entropy approach for complexity analysis in clean energy markets , 2017, Appl. Soft Comput..

[27]  Ling Tang,et al.  A Novel CEEMD-Based EELM Ensemble Learning Paradigm for Crude Oil Price Forecasting , 2015, Int. J. Inf. Technol. Decis. Mak..

[28]  He Nie,et al.  Dynamic linkages among the gold market, US dollar and crude oil market , 2018 .

[29]  Yudong Wang,et al.  Multifractal detrended cross-correlations between crude oil market and Chinese ten sector stock markets , 2016 .

[30]  K. Lai,et al.  A new approach for crude oil price analysis based on Empirical Mode Decomposition , 2008 .

[31]  Ronald Hagen,et al.  How is the international price of a particular crude determined , 1994 .

[32]  Zebin Yang,et al.  Online big data-driven oil consumption forecasting with Google trends , 2019, International Journal of Forecasting.

[33]  Lean Yu,et al.  Assessing Potentiality of Support Vector Machine Method in Crude Oil Price Forecasting , 2017 .

[34]  Ling Tang,et al.  Forecasting Oil Price Trends with Sentiment of Online News Articles , 2017, Asia Pac. J. Oper. Res..

[35]  N. Huang,et al.  A new view of nonlinear water waves: the Hilbert spectrum , 1999 .

[36]  K. Lai,et al.  Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm , 2008 .