A non-iterative decomposition-ensemble learning paradigm using RVFL network for crude oil price forecasting

Abstract To address time consuming and parameter sensitivity in the emerging decomposition- ensemble models, this paper develops a non-iterative learning paradigm without iterative training process. Different from the most existing decomposition-ensemble models using statistical or iterative approaches as individual forecasting tools, the proposed work otherwise employs the efficient and fast non-iterative algorithm—random vector functional link (RVFL) network with randomly fixed weights and direct input-output links. Three major steps are included: decomposition via ensemble empirical mode decomposition (EEMD), prediction via RVFL network, and ensemble via linear addition. With crude oil price as studying sample, the proposed EEMD-based RVFL network performs significantly better in terms of prediction accuracy than not only single algorithms such as RVFL network, extreme learning machine (ELM), kernel ridge regression, random forest, back propagation neural network, least square support vector regression, and autoregressive integrated moving average, but also their respective EEMD-based ensemble variants. As for speed ranking, RVFL network developed in 1994 ranks the first among all the listed methods, and EEMD-based RVFL network defeats all the ensemble methods and most single methods, possibly due to the fact that RVFL network with direct input-output links needs far less enhancement nodes and hence a shorter computational time than those without the direct links such as the ELM developed in 2006.

[1]  Dejan J. Sobajic,et al.  Learning and generalization characteristics of the random vector Functional-link net , 1994, Neurocomputing.

[2]  Yoh-Han Pao,et al.  Unconstrained word-based approach for off-line script recognition using density-based random-vector functional-link net , 2000, Neurocomputing.

[3]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[4]  Haiyan Lu,et al.  Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model , 2012 .

[5]  Dirk Husmeier,et al.  Neural Networks for Conditional Probability Estimation , 1999, Perspectives in Neural Computing.

[6]  Ponnuthurai N. Suganthan,et al.  Random vector functional link network for short-term electricity load demand forecasting , 2016, Inf. Sci..

[7]  Jianzhou Wang,et al.  Forecasting wind speed using empirical mode decomposition and Elman neural network , 2014, Appl. Soft Comput..

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

[9]  Dianhui Wang,et al.  Distributed learning for Random Vector Functional-Link networks , 2015, Inf. Sci..

[10]  Zhitao Liu,et al.  A Fast Grid Search Method in Support Vector Regression Forecasting Time Series , 2006, IDEAL.

[11]  Kwok-wing Chau,et al.  Improving Forecasting Accuracy of Annual Runoff Time Series Using ARIMA Based on EEMD Decomposition , 2015, Water Resources Management.

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

[13]  C. L. Philip Chen,et al.  A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction , 1999, IEEE Trans. Syst. Man Cybern. Part B.

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

[15]  Emilio Soria-Olivas,et al.  Hardware implementation methods in Random Vector Functional-Link Networks , 2013, Applied Intelligence.

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

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

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

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

[20]  Shan Juan Xie,et al.  A High Accuracy Pedestrian Detection System Combining a Cascade AdaBoost Detector and Random Vector Functional-Link Net , 2014, TheScientificWorldJournal.

[21]  Qiang Liu,et al.  Particle size estimate of grinding processes using random vector functional link networks with improved robustness , 2015, Neurocomputing.

[22]  Okan K. Ersoy,et al.  A statistical self-organizing learning system for remote sensing classification , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[23]  P. N. Suganthan,et al.  A Comparative Study of Empirical Mode Decomposition-Based Short-Term Wind Speed Forecasting Methods , 2015, IEEE Transactions on Sustainable Energy.

[24]  Tianyou Chai,et al.  Multisource Data Ensemble Modeling for Clinker Free Lime Content Estimate in Rotary Kiln Sintering Processes , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[25]  Le Zhang,et al.  A survey of randomized algorithms for training neural networks , 2016, Inf. Sci..

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

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

[28]  Ponnuthurai Nagaratnam Suganthan,et al.  Electricity load demand time series forecasting with Empirical Mode Decomposition based Random Vector Functional Link network , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[29]  P. N. Suganthan,et al.  A comprehensive evaluation of random vector functional link networks , 2016, Inf. Sci..

[30]  Dianhui Wang,et al.  Fast decorrelated neural network ensembles with random weights , 2014, Inf. Sci..

[31]  R. C. Gardner,et al.  Type I Error Rate Comparisons of Post Hoc Procedures for I j Chi-Square Tables , 2000 .

[32]  Guoyin Wang,et al.  Erratum to “Experimental Analyses of the Major Parameters Affecting the Intensity of Outbursts of Coal and Gas” , 2014, The Scientific World Journal.

[33]  Ling Tang,et al.  A novel decomposition ensemble model with extended extreme learning machine for crude oil price forecasting , 2016, Eng. Appl. Artif. Intell..

[34]  Yuehjen E. Shao,et al.  Forecasting Computer Products Sales by Integrating Ensemble Empirical Mode Decomposition and Extreme Learning Machine , 2012 .

[35]  M. Friedman A Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings , 1940 .

[36]  Ricardo Fraiman,et al.  An anova test for functional data , 2004, Comput. Stat. Data Anal..

[37]  D. Bui,et al.  A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. , 2015 .

[38]  B. K. Panigrahi,et al.  A hybrid wavelet-ELM based short term price forecasting for electricity markets , 2014 .

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

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

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

[42]  Qinghua Hu,et al.  Ultra-short-term wind speed prediction based on multi-scale predictability analysis , 2016, Cluster Computing.

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

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

[45]  Danilo Comminiello,et al.  A semi-supervised random vector functional-link network based on the transductive framework , 2016, Inf. Sci..