A novel decomposition-ensemble approach to crude oil price forecasting with evolution clustering and combined model

  • Jiaming Zhu
  • Jinpei Liu
  • Peng Wu
  • Huayou ChenEmail author
  • Ligang Zhou
Original Article


In order to deal with non-stationary and chaotic series, a hybrid forecasting approach is proposed in this study, which integrates ensemble empirical mode decomposition (EEMD) and optimal combined forecasting model (CFM). The proposed approach introduces a new intrinsic mode functions (IMFs) reconstruction method by using evolutionary clustering algorithm, and utilizes optimal combined model to forecast sub-series. Firstly, the EEMD technique is employed to sift the IMFs and a residue. Secondly, the comprehensive contribution index (CCI) of each IMF is calculated and IMFs are further reconstructed by evolutionary clustering algorithm according to CCI of each IMF. Then, a new sub-series called virtual intrinsic mode functions (VIMFs) is defined and obtained. Thirdly, the optimal combined forecasting model is developed to forecast the VIMFs and residues. In the end, the final forecasting results are obtained by summing the forecasts of VIMFs and residue. For illustration and comparison, the West Texas Intermediate (WTI) crude oil price data are shown as a numerical example. The research results show that the proposed approach outperforms benchmark models in terms of some forecasting assessment measures. Therefore, the proposed hybrid approach can be utilized as an effective model for the forecasting of crude oil price.


Hybrid forecasting approach Ensemble empirical mode decomposition Mode reconstruction Optimal combined model Crude oil price 



Artificial neural networks


Intrinsic mode function


Support vector regression


Combined forecasting model

DM test

Diebold–Mariano test


Sum of square error


Mean absolute error


Root mean square error


Ensemble empirical mode decomposition


Virtual intrinsic mode function


Nonlinear autoregressive neural network


General regression neural network


Artificial neural networks


Comprehensive contribution index


Induced ordered weighted averaging


Mean absolute percentage error



The work was supported by National Natural Science Foundation of China (Nos. 71871001, 61502003, 71771001, 71701001, 71501002), University Provincial Natural Science Research Project of Anhui Province (No. KJ2017A026).

Compliance with ethical standards

Conflict of Interest

The authors declared that they have no conflicts of interest to this work.


  1. 1.
    Miao H, Ramchander S, Wang T, Yang D (2017) Influential factors in crude oil price forecasting. Energy Econ 68:77–88Google Scholar
  2. 2.
    He KJ, Yu L, Lai KK (2012) Crude oil price analysis and forecasting using wavelet decomposed ensemble model. Energy 46(1):564–574Google Scholar
  3. 3.
    Yu L, Zhao Y, Tang L (2014) A compressed sensing based AI learning paradigm for crude oil price forecasting. Energy Econ 46:236–245Google Scholar
  4. 4.
    Xiang Y, Zhuang XH (2013) Application of ARIMA model in short-term prediction of international crude oil price. Adv Mater Res 798:979–982Google Scholar
  5. 5.
    Nomikos N, Andriosopoulos K (2012) Modelling energy spot prices: empirical evidence from nymex. Energy Econ 34(4):1153–1169Google Scholar
  6. 6.
    Ye M, Zyren J, Shore J (2002) Forecasting crude oil spot price using OCED petroleum inventory levels. Int Adv Econ Res 8(4):324–333Google Scholar
  7. 7.
    Wang X, Cao W (2018) Non-iterative approaches in training feed-forward neural networks and their applications. Soft Comput 22:3473–3476zbMATHGoogle Scholar
  8. 8.
    Wang C, Hu Q, Wang X, Chen D, Qian Y, Dong Z (2018) Feature selection based on neighborhood discrimination index. IEEE Trans Neural Nete Learn 29(7):2986–2999MathSciNetGoogle Scholar
  9. 9.
    Cao W, Wang X, Ming Z, Gao J (2018) A review on neural networks with random weights. Neurocomputing 275:278–287Google Scholar
  10. 10.
    Xiong T, Bao YK, Hu ZY, Chiong R (2015) Forecasting interval time series using a fully complex-valued RBF neural network with DPSO and PSO algorithms. Inform Sci 305:77–92Google Scholar
  11. 11.
    Das SP, Padhy S (2018) A novel hybrid model using teaching learning-based optimization and a support vector machine for commodity futures index forecasting. Int J Mach Learn Cyb 9(1):97–111Google Scholar
  12. 12.
    Singh P (2016) Rainfall and financial forecasting using fuzzy time series and neural networks based model. Int J Mach Learn Cyb 9(3):1–16Google Scholar
  13. 13.
    Barunk J, Malinsk B (2016) Forecasting the term structure of crude oil futures prices with neural networks. Appl Energy 164:366–379Google Scholar
  14. 14.
    Chiroma H, Abdulkareem S, Herawan T (2015) Evolutionary neural network model for west texas intermediate crude oil price prediction. Appl Energy 142:266–273Google Scholar
  15. 15.
    Fan L, Pan S, Li Z, Li H (2016) An ICA-based support vector regression scheme for forecasting crude oil prices. Technolo Forecas Soc Change 112:245–253Google Scholar
  16. 16.
    Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q (1998) The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond A 454:903–995MathSciNetzbMATHGoogle Scholar
  17. 17.
    Wu Z, Huang NE (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adaptive Data Anal 1(1):1–41Google Scholar
  18. 18.
    Song J, Wang JZ, Lu H (2018) A novel combined model based on advanced optimization algorithm for short-term wind speed forecasting. Appl Energy 215:643–658Google Scholar
  19. 19.
    Zhang X, Wang JZ (2018) A novel decomposition-ensemble model for forecasting short-term load-time series with multiple seasonal patterns. Appl Soft Comput 65:478–494Google Scholar
  20. 20.
    Che JX, Wang JZ (2014) Short-term load forecasting using a kernel-based support vector regression combination model. Appl Energy 132:602–609Google Scholar
  21. 21.
    Yu L, Wang ZS, Tang L (2015) A decompositionCensemble model with data-characteristic-driven reconstruction for crude oil price forecasting. Appl Energy 156:251–267Google Scholar
  22. 22.
    Zhao Y, Li JP, Yu L (2017) A deep learning ensemble approach for crude oil price forecasting. Energy Econ 66:9–16Google Scholar
  23. 23.
    Tang L, Wu Y, Yu L (2018) A non-iterative decomposition-ensemble learning paradigm using RVFL network for crude oil price forecasting. Appl Soft Comput 70:1097–1108Google Scholar
  24. 24.
    Ding YS (2018) A novel decompose-ensemble methodology with AIC-ANN approach for crude oil forecasting. Energy 154:328–336Google Scholar
  25. 25.
    Yu L, Dai W, Tang L (2016) A novel decomposition ensemble model with extended extreme learning machine for crude oil price forecasting. Eng Appl Artif Intell 47:110–121Google Scholar
  26. 26.
    Zhang JL, Zhang YJ, Zhang L (2015) A novel hybrid method for crude oil price forecasting. Energy Econ 49:649–659Google Scholar
  27. 27.
    Wang MG, Zhao LF, Du RJ, Wang C, Chen L, Tian LX, Stanley HE (2018) A novel hybrid method of forecasting crude oil prices using complex network science and artificial intelligence algorithms. Appl Energy 220:480–495Google Scholar
  28. 28.
    Wang J, Li X, Hong T, Wang SY (2018) A semi-heterogeneous approach to combining crude oil price forecasts. Inform Sci 460:279–292MathSciNetGoogle Scholar
  29. 29.
    Li JR, Wang R, Wang JZ, Li YF (2018) Analysis and forecasting of the oil consumption in China based on combination models optimized by artificial intelligence algorithms. Energy 144:243–264Google Scholar
  30. 30.
    Jianwei E, Bao YL, Ye JM, Li YF (2017) Crude oil price analysis and forecasting based on variational mode decomposition and independent component analysis. Physica A 484:412–427Google Scholar
  31. 31.
    Zhang Y, Ma F, Shi B, Huang D (2018) Forecasting the prices of crude oil: an iterated combination approach. Energy Econ 70:472–483Google Scholar
  32. 32.
    Yu L, Wang SY, Lai KK (2008) Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm. Energy Econ 30:2623–2635zbMATHGoogle Scholar
  33. 33.
    Tang L, Dai W, Yu L, Wang SY (2015) A novel CEEMD-based EELM ensemble learning paradigm for crude oil price forecasting. Int J Inf Technol Decis 14(01):141–169Google Scholar
  34. 34.
    Safari A, Davallou M (2018) Oil price forecasting using a hybrid model. Energy 148:49–58Google Scholar
  35. 35.
    Chen Y, Zhang C, He KJ, Zheng A (2018) Multi-step-ahead crude oil price forecasting using a hybrid grey wave model. Physica A 501:98–110Google Scholar
  36. 36.
    Yu L, Xu H, Tang L (2017) LSSVR ensemble learning with uncertain parameters for crude oil price forecasting. Appl Soft Comput 56:692–701Google Scholar
  37. 37.
    Xian L, He KJ, Lai KK (2016) Gold price analysis based on ensemble empirical model decomposition and independent component analysis. Physica A 454:11–23Google Scholar
  38. 38.
    Bates J, Granger C (1969) Combination of forecasts. Oper Res 20(4):451–468Google Scholar
  39. 39.
    Chen HY (2008) Validity principle theory of combination forecasting and its application. Science Press, BeijingGoogle Scholar
  40. 40.
    Chen HY, Jin LH, Li X, Yao MJ (2011) The optimal interval combination forecasting model based on closeness degree and IOWHA operator under the uncertain environment. Grey Syst Theory A 1(3):250–260Google Scholar
  41. 41.
    Silva JDA, Hruschka ER, Gama J (2016) An evolutionary algorithm for clustering data streams with a variable number of clusters. Expert Syst Appl 67:228–238Google Scholar
  42. 42.
    Ahmed A, Khalid M (2017) Multi-step ahead wind forecasting using nonlinear autoregressive neural networks. Energy Procedia 134:192–204Google Scholar
  43. 43.
    Specht D (1991) A general regression neural network. IEEE T Neural Netw 2(6):568–576Google Scholar
  44. 44.
    Holt CC (2004) Forecasting seasonals and trends by exponentially weighted moving averages. Int J Forecast 20(1):5–10Google Scholar
  45. 45.
    Xu YZ, Yang WD, Wang JZ (2016) Air quality early-warning system for cities in china. Atmos Environ 148:239–257Google Scholar
  46. 46.
    Diebold F, Mariano R (1995) Comparing predictive accuracy. J Bus Econ Stat 13(3):253–263Google Scholar
  47. 47.
    Che JX (2015) Optimal sub-models selection algorithm for combination forecasting model. Neurocomputing 151:364–375Google Scholar
  48. 48.
    Lan Y, Zhao R, Tang W (2011) Minimum risk criterion for uncertain production planning problems. Comput Ind Eng 61(3):591–599Google Scholar
  49. 49.
    Yager RR, Filev DP (1999) Induced ordered weighted averaging operators. IEEE T Syst Man Cybren B 29(2):141–150Google Scholar
  50. 50.
    Zhu BZ, Ye SX, Wang P, He KJ, Zhang T, Wei YM (2018) A novel multiscale nonlinear ensemble leaning paradigm for carbon price forecasting. Energy Econ 70:143–157Google Scholar
  51. 51.
    Zhu BZ, Han D, Wang P, Wu ZC, Zhang T, Wei YM (2017) Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression. Appl Energy 191:521–530Google Scholar
  52. 52.
    Xiong T, Li CG, Bao YK (2018) Seasonal forecasting of agricultural commodity price using a hybrid STL and ELM method: Evidence from the vegetable market in China. Neurocomputing 275:2831–2844Google Scholar
  53. 53.
    Karsoliya S (2012) Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. Int J Eng Trends Technol 3(6):714–717Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Jiaming Zhu
    • 1
  • Jinpei Liu
    • 2
  • Peng Wu
    • 1
  • Huayou Chen
    • 1
    Email author
  • Ligang Zhou
    • 1
    • 3
  1. 1.School of Mathematical SciencesAnhui UniversityHefeiChina
  2. 2.School of BusinessAnhui UniversityHefeiChina
  3. 3.China Institute of Manufacturing DevelopmentNanjing University of Information Science and TechnologyNanjingChina

Personalised recommendations