Soft Computing

, Volume 22, Issue 16, pp 5323–5333 | Cite as

A combined neural network model for commodity price forecasting with SSA

  • Jue WangEmail author
  • Xiang Li


Commodity price forecasting is challenging full of volatility, uncertainty and complexity. In this paper, a novel modeling framework is proposed to predict the market price of commodity futures. Three types of commodity are selected as representatives: corn from agricultural products, gold from industrial metal and crude oil from energy. We decomposed the original series into independent components at various scales using singular spectrum analysis (SSA). A SSA-causality test is introduced to investigate the mutual influence between commodity futures prices. Additionally, using the SSA-smoothing scheme, we construct combined neural network models including back propagation, radial basis function and wavelet neural network to predict the commodity price. The experimental results illustrate that neural network models with the SSA outperform the benchmarks in terms of distinct measures.


SSA Neural network Commodity price Forecasting 



This work was supported by Youth Innovation Promotion Association, CAS, National Center for Mathematics and Interdisciplinary Sciences (NCMIS), CAS and the National Natural Science Foundation of China (NSFC Nos. 71771208, 71271202).

Compliance with ethical standards

Conflict of interest

Authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants performed by any of the authors.


  1. Chen Y, Yang B, Dong J (2006) Time-series prediction using a local linear wavelet neural network. Neurocomputing 69(46):449–465CrossRefGoogle Scholar
  2. Ding Y, Jiang Z, Zhu Y (1998) Experiment on short term climatic prediction to SSTA over the Nino oceanic region. J Trop Meteorol 4:289–296Google Scholar
  3. Hassani H, Thomakos D (2010) A review on singular spectrum analysis for economic and financial time series. Stat Interface 3(3):377–397MathSciNetCrossRefzbMATHGoogle Scholar
  4. Kristjanpoller W, Minutolo MC (2015) Gold price volatility: a forecasting approach using the artificial neural network–GARCH model. Expert Syst Appl 42(20):7245–7251CrossRefGoogle Scholar
  5. Lin WM, Gow HJ, Tsai MT (2010) An enhanced radial basis function network for short-term electricity price forecasting. Appl Energy 87(10):3226–3234CrossRefGoogle Scholar
  6. Maghyereh A (2004) Oil price shocks and emerging stock markets: a generalized VAR approach. Int J Appl Econom Quant Stud 1(2):27–40Google Scholar
  7. Maghyereh A (2006) Oil price shocks and emerging stock markets: a generalized VAR approach. Palgrave Macmillan, New YorkGoogle Scholar
  8. Motlaghi S, Jalali F, Ahmadabadi MN (2008) An expert system design for a crude oil distillation column with the neural networks model and the process optimization using genetic algorithm framework. Expert Syst Appl 35(4):1540–1545CrossRefGoogle Scholar
  9. Reboredo JC, Rivera-Castro MA (2013) A wavelet decomposition approach to crude oil price and exchange rate dependence. Econ Model 32(32):42–57CrossRefGoogle Scholar
  10. Salisu AA, Oloko TF (2015) Modeling oil pricec—US stock nexus: a VARMA–BEKK–AGARCH approach. Energy Econ 50:1–12CrossRefGoogle Scholar
  11. Vautard R, Yiou P, Ghil M (1992) Singular-spectrum analysis: a toolkit for short, noisy chaotic signals. Physica D 58(14):95–126CrossRefGoogle Scholar
  12. Wang S, Yu L, Lai KK (2005) Crude oil price forecasting with TEI@I methodology. J Syst Sci Complex 18(2):145–166zbMATHGoogle Scholar
  13. Wen F, Yang X, Gong X, Lai KK (2017) Multi-scale volatility feature analysis and prediction of gold price. Int J Inf Technol Dec Mak 16(1):205–223CrossRefGoogle Scholar
  14. Xu X, Zhang W, Li N, Xu H (2015) A bi-level programming model of resource matching for collaborative logistics network in supply uncertainty environment. J Frank Inst 352(9):3873–3884MathSciNetCrossRefGoogle Scholar
  15. Yu L, Wang S, Lai KK (2008) Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm. Energy Econ 30(5):2623–2635CrossRefzbMATHGoogle Scholar
  16. Zeng L, Dan-Di MA, Liu ZX (2010) Gold price forecast based on improved BP neural network. Comput Simul 27(9):200–203Google Scholar
  17. Zhang YJ, Wang J (2015) Exploring the WTI crude oil price bubble process using the Markov regime switching model. Physica A 421(1):377–387MathSciNetCrossRefGoogle Scholar
  18. Zhang K, Yong YU (2010) Application of wavelet neural network in prediction of gold price. Comput Eng Appl 7:154–169Google Scholar
  19. Zhang X, Lai KK, Wang SY (2008) A new approach for crude oil price analysis based on empirical mode decomposition. Energy Econ 30(3):905–918CrossRefGoogle Scholar
  20. Zhang JL, Zhang YJ, Zhang L (2015) A novel hybrid method for crude oil price forecasting. Energy Econ 49:649–659Google Scholar
  21. Zhang X, Wang J, Zhang K (2017) Short-term electric load forecasting based on singular spectrum analysis and support vector machine optimized by cuckoo search algorithm. Electr Power Syst Res 146:270–285CrossRefGoogle Scholar
  22. Zhu HR, Jiang ZH, Zhang Q, Xiao-Hui JU (2010) MJO index forecasting based on SSA-AR model. J Trop Meteorol 6:245–260Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.CEFS, MADISAcademy of Mathematics and Systems Science, Chinese Academy of SciencesBeijingChina
  2. 2.School of Economics and ManagementUniversity of Chinese Academy of SciencesBeijingChina

Personalised recommendations