Neural Processing Letters

, Volume 41, Issue 2, pp 249–258 | Cite as

Recurrent Multiplicative Neuron Model Artificial Neural Network for Non-linear Time Series Forecasting

  • Erol EgriogluEmail author
  • Ufuk Yolcu
  • Cagdas Hakan Aladag
  • Eren Bas


Artificial neural networks (ANN) have been widely used in recent years to model non-linear time series since ANN approach is a responsive method and does not require some assumptions such as normality or linearity. An important problem with using ANN for time series forecasting is to determine the number of neurons in hidden layer. There have been some approaches in the literature to deal with the problem of determining the number of neurons in hidden layer. A new ANN model was suggested which is called multiplicative neuron model (MNM) in the literature. MNM has only one neuron in hidden layer. Therefore, the problem of determining the number of neurons in hidden layer is automatically solved when MNM is employed. Also, MNM can produce accurate forecasts for non-linear time series. ANN models utilized for non-linear time series have generally autoregressive structures since lagged variables of time series are generally inputs of these models. On the other hand, it is a well-known fact that better forecasts for real life time series can be obtained from models whose inputs are lagged variables of error. In this study, a new recurrent multiplicative neuron neural network model is firstly proposed. In the proposed method, lagged variables of error are included in the model. Also, the problem of determining the number of neurons in hidden layer is avoided when the proposed method is used. To train the proposed neural network model, particle swarm optimization algorithm was used. To evaluate the performance of the proposed model, it was applied to a real life time series. Then, results produced by the proposed method were compared to those obtained from other methods. It was observed that the proposed method has superior performance to existing methods.


Artificial neural networks Forecasting Multiplicative neuron model Non-linear time series Recurrent neural networks 



The authors would like to thank the anonymous reviewers and editors of journal for their valuable comments and suggestions to improve the quality of the paper.


  1. 1.
    Aladag CH (2011) A new architecture selection method based on tabu search for artificial neural networks. Expert Syst Appl 38:3287–3293CrossRefGoogle Scholar
  2. 2.
    Aladag CH, Egrioglu E (eds) (2012) Advances in time series forecasting. Bentham Science Publishers Ltd., Oak Park, USA. Accessed 24 Jan 2014
  3. 3.
    Aladag CH, Egrioglu E, Gunay S, Basaran MA (2010) Improving weighted information criterion by using optimization. J Comput Appl Math 233:2683–2687CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Aladag CH, Yolcu U, Egrioglu E (2013) A new multiplicative seasonal neural network model based on particle swarm optimization. Neural Process Lett 37(3):251–262CrossRefGoogle Scholar
  5. 5.
    Box GEP, Jenkins GM (1976) Time series analysis: forecasting and control. Holden-Day, San FranciscozbMATHGoogle Scholar
  6. 6.
    BuHamra S, Smaoui N, Gabr M (2003) The Box–Jenkins analysis and neural networks: prediction and time series modeling. Appl Math Model 27:805–815CrossRefzbMATHGoogle Scholar
  7. 7.
    Crone S, Kourentzes N (2010) Naive support vector regression and multilayer perceptron benchmarks for the 2010 neural network grand competition (NNGC) on time series prediction. In: Proceedings of the international joint Conference on neural networks, IJCNN’10, Barcelona, IEEE, New YorkGoogle Scholar
  8. 8.
    Crone S, Nikolopoulos K, Hibon M (2011) New evidence on the accuracy of computational intelligence for monthly time series prediction—results of the NN3 forecasting competition. Int J Forecast 27(3):635–660CrossRefGoogle Scholar
  9. 9.
    Egrioglu E, Aladag CH, Gunay S (2008) A new model selection strategy in artificial neural network. Appl Math Comput 195:591–597CrossRefzbMATHMathSciNetGoogle Scholar
  10. 10.
    Egrioglu E, Aladag CH, Yolcu U, Başaran A, Uslu VR (2009) A new hybrid approach based on SARIMA and partial high order bivariate fuzzy time series forecasting model. Expert Syst Appl 36:7424–7434CrossRefGoogle Scholar
  11. 11.
    Elman JL (1990) Finding structure in time. Cogn Sci 14(2):179–211CrossRefGoogle Scholar
  12. 12.
    Giles CL, Lawrence S, Tsoi AC (2001) Noisy time series prediction using recurrent neural networks and grammatical inference. Mach Learn 44(1/2):161–183CrossRefzbMATHGoogle Scholar
  13. 13.
    Janacek G (2001) Practical time series. Oxford University Press Inc., New YorkzbMATHGoogle Scholar
  14. 14.
    Jordan MI (1986) Serial order: a parallel distributed processing approach (Tech. Rep. No. 8604). Institute for Cognitive Science, University of California, San DiegoGoogle Scholar
  15. 15.
    Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of IEEE international conference on neural networks. IEEE Press, Piscataway, pp 1942–1948Google Scholar
  16. 16.
    Khashei M, Bijari M (2010) An artificial network (p, d, q) model for time series forecasting. Expert Syst Appl 37:479–489CrossRefGoogle Scholar
  17. 17.
    Lin T, Horne BG, Giles CL (1998) How embedded memory in recurrent neural network architectures helps learning long-term temporal dependencies. Neural Netw 11(5):861–868CrossRefGoogle Scholar
  18. 18.
    Yadav RN, Kalra PK, John J (2007) Time series prediction with single multiplicative neuron model. Appl Soft Comput 7:1157–1163CrossRefGoogle Scholar
  19. 19.
    Yolcu U, Aladag CH, Egrioglu E (2013) A new linear & nonlinear artificial neural network model for time series forecasting. Decis Support Syst 54:1340–1347CrossRefGoogle Scholar
  20. 20.
    Zemouri R, Patic PC (2010) Prediction error feedback for time series prediction: a way to improve the accuracy of predictions. In: Grigoriu M, Mladenov V, Bulucea CA, Martin O, Mastorakis N (eds) Proceedings of the 4th conference on European computing conference (ECC’10), Scientific World, Academy Engineering, Society (WSEAS), Stevens Point, WI, USA, pp 58–62Google Scholar
  21. 21.
    Zhang G (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175CrossRefzbMATHGoogle Scholar
  22. 22.
    Zhang G, Patuwo BE, Hu YM (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14:35–62CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Erol Egrioglu
    • 1
    Email author
  • Ufuk Yolcu
    • 2
  • Cagdas Hakan Aladag
    • 3
  • Eren Bas
    • 4
  1. 1.Department of Statistics, Faculty of Arts and ScienceOndokuz Mayıs University SamsunTurkey
  2. 2.Department of Statistics, Faculty of ScienceAnkara University AnkaraTurkey
  3. 3.Department of Statistics, Faculty of ScienceHacettepe University AnkaraTurkey
  4. 4.Department of Statistics, Faculty of Arts and ScienceGiresun University GiresunTurkey

Personalised recommendations