Modelling and Trading the Greek Stock Market with Hybrid ARMA-Neural Network Models

  • Christian L. DunisEmail author
  • Jason Laws
  • Andreas Karathanasopoulos
Part of the Springer Optimization and Its Applications book series (SOIA, volume 70)


The motivation for this chapter is to investigate the use of alternative novel neural network architectures when applied to the task of forecasting and trading the ASE 20 Greek Index using only autoregressive terms as inputs. This is done by benchmarking the forecasting performance of six different neural network designs representing aHigher Order Neural Network (HONN), aRecurrent Network (RNN), a classicMultilayer Perceptron (MLP), a Hybrid Higher Order Neural Network, a Hybrid Recurrent Neural Network and a Hybrid Multilayer Perceptron Neural Network with some traditional techniques, either statistical such as an autoregressive moving average model (ARMA) or technical such as a moving average convergence/divergence model (MACD), plus a naïve trading strategy. More specifically, the trading performance of all models is investigated in a forecast and trading simulation on ASE 20 fixing time series over the period 2001–2008 using the last one and a half year for out-of-sample testing. We use the ASE 20 daily fixing as many financial institutions are ready to trade at this level and it is therefore possible to leave orders with a bank for business to be transacted on that basis. As it turns out, the hybrid-HONNs do remarkably well and outperform all other models in a simple trading simulation exercise. However, when more sophisticatedtrading strategies usingconfirmation filters andleverage are applied, the hybrid-HONN network produces better results and outperforms all other neural network and traditional statistical models in terms of annualised return.


Transaction Cost Trading Strategy Forecast Accuracy Trading Performance ARMA Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    O. Adam, L. Zarader, M. Milgram, Identification and prediction of non-linear models with recurrent neural networks, in New Trends in Neural Computation, ed. by J. Mira, J. Cabestany, A. Prieto. Lecture Notes in Computer Science, vol. 686 (Springer, Berlin, 1993), pp. 531–535Google Scholar
  2. 2.
    C. Bishop, Mixture density networks. Technical report NCRG/4288, Neural Computing Research Group, Aston University (1994)Google Scholar
  3. 3.
    G. Box, G. Jenkins, G. Gregory, Time Series Analysis: Forecasting and Control (Prentice-Hall, New Jersey, 1994)Google Scholar
  4. 4.
    G. Brown, J. Wyatt, R. Harris, X. Yao, Diversity creation methods: A survey and categorization. Inf. Fusion 6, 5–20 (2005)Google Scholar
  5. 5.
    R. Clemen, Combining forecasts: A review and annotated bibliography. Int. J. Forecast. 5, 559–583 (1989)Google Scholar
  6. 6.
    J. Connor, L. Atlas, Recurrent neural networks and time series prediction, in Proceedings of the International Joint Conference on Neural Networks (1993), pp. 301–306Google Scholar
  7. 7.
    C. Dunis, Y. Chen, Alternative volatility models for risk management and trading: Application to the EUR/USD and USD/JPY rates. Derivatives Use, Trading and Regulation 11(2), 126–156 (2005)Google Scholar
  8. 8.
    C. Dunis, X. Huang, Forecasting and trading currency volatility: An application of recurrent neural regression and model combination. J. Forecast. 21(5), 317–354 (2002)Google Scholar
  9. 9.
    C. Dunis, J. Laws, B. Evans, Modelling and trading the gasoline crack spread: A non-linear story. Derivatives Use, Trading and Regulation 12, 126–145 (2006)Google Scholar
  10. 10.
    C. Dunis, J. Laws, B. Evans, Trading futures spreads: An application of correlation and threshold filters. Appl. Financ. Econ. 16, 1–12 (2006)Google Scholar
  11. 11.
    C. Dunis, J. Laws, G. Sermpinis, Modelling and trading the EUR/USD exchange rate at the ECB fixing. Eur. J. Finance 16(6), 541–560 (2010)Google Scholar
  12. 12.
    C. Dunis, J. Laws, G. Sermpinis, Higher order and recurrent neural architectures for trading the EUR/USD exchange rate. Quant. Finance 11(4), 615–629 (2011)Google Scholar
  13. 13.
    J.L. Elman, Finding structure in time. Cognit. Sci. 14, 179–211 (1990)Google Scholar
  14. 14.
    S. Fatima, G. Hussain, Statistical models of KSE100 index using hybrid financial systems. Neurocomputing 7, 2742–2746 (2008)Google Scholar
  15. 15.
    J. Fulcher, M. Zhang, S. Xu, Application of higher-order neural networks to financial time series, in Artificial Neural Networks in Finance and Manufacturing, ed. by J. Kamruzzaman, R. Begg, R. Sarker (Idea Group, Hershey, 2006), pp. 80–108Google Scholar
  16. 16.
    L. Giles, T. Maxwell, Learning, invariance and generalization in higher order neural networks. Appl. Optic. 26, 4972–4978 (1987)Google Scholar
  17. 17.
    J. Hansen, R. Nelson, Time-series analysis with neural networks and ARIMA-neural network hybrids. J. Exp. Theor. Artif. Intell. 15(3), 315–330 (2003)Google Scholar
  18. 18.
    H. Hibbert, C. Pedreira, R. Souza, Combining neural networks and arima models for hourly temperature forecast, in IEEE International Joint Conference on Neural Networks (IJCNN’00), vol. 4 (2000), pp. 414–419Google Scholar
  19. 19.
    M. Hibon, T. Evgeniou, To combine or not to combine: Selecting among forecasts and their combinations. Int. J. Forecast. 22, 15–24 (2005)Google Scholar
  20. 20.
    I. Kaastra, M. Boyd, Designing a neural network for forecasting financial and economic time series. Neurocomputing 10, 215–236 (1996)Google Scholar
  21. 21.
    K. Kamijo, T. Tanigawa, Stock price pattern recognition: A recurrent neural network approach, in Proceedings of the International Joint Conference on Neural Networks (1990), pp. 1215–1221Google Scholar
  22. 22.
    N. Karayiannis, A. Venetsanopoulos, On the training and performance of high-order neural networks. Math. Biosci. 129, 143–168 (1994)Google Scholar
  23. 23.
    A. Knowles, A. Hussein, W. Deredy, P. Lisboa, C.L. Dunis, Higher-order neural networks with Bayesian confidence measure for prediction of EUR/USD exchange rate, in Artificial Higher Order Neural networks for Economics and Business, ed. by M. Zhang (Idea Group, Hershey, 2009), pp. 48–59Google Scholar
  24. 24.
    E. Kosmatopoulos, M. Polycarpou, M. Christodoulou, P. Ioannou, High-order neural network structures for identification of dynamical systems. IEEE Trans. Neural Network 6, 422–431 (1995)Google Scholar
  25. 25.
    A. Lindemann, C. Dunis, P. Lisboa, Level estimation, classification and probability distribution architectures for trading the EUR/USD exchange rate. Neural Network Comput. Appl. 14(3), 256–271 (2004)Google Scholar
  26. 26.
    S. Makridakis, Why combining works? Int. J. Forecast. 5, 601–603 (1989)Google Scholar
  27. 27.
    S. Makridakis, A. Anderson, R. Carbone, R. Fildes, M. Hibdon, R. Lewandowski, J. Newton, E. Parzen, R. Winkler, The accuracy of extrapolation (time series) methods: Results of a forecasting competition. J. Forecast. 1, 111–153 (1982)Google Scholar
  28. 28.
    P. Newbold, C.W.J. Granger, Experience with forecasting univariate time series and the combination of forecasts (with discussion). J. Stat. 137, 131–164 (1974)Google Scholar
  29. 29.
    F.C. Palm, A. Zellner, To combine or not to combine? issues of combining forecasts. J. Forecast. 11, 687–701 (1992)Google Scholar
  30. 30.
    R. Pindyck, D. Rubinfeld, Econometric Models and Economic Forecasts, 4th edn. (McGraw-Hill, New York, 1988)Google Scholar
  31. 31.
    D. Psaltis, C. Park, J. Hong, Higher order associative memories and their optical implementations. Neural Network 1, 149–163 (1988)Google Scholar
  32. 32.
    N. Redding, A. Kowalczyk, T. Downs, Constructive higher-order network algorithm that is polynomial time. Neural Network 6, 997–1010 (1993)Google Scholar
  33. 33.
    A.F. Shapiro, A hitchhikers guide to the techniques of adaptive nonlinear models. Insur. Math. Econ. 26, 119–132 (2000)Google Scholar
  34. 34.
    P. Tenti, Forecasting foreign exchange rates using recurrent neural networks. Appl. Artif. Intell. 10, 567–581 (1996)Google Scholar
  35. 35.
    N. Terui, H. van Dijk, Combined forecasts from linear and nonlinear time series models. Int. J. Forecast. 18, 421–438 (2002)Google Scholar
  36. 36.
    H. Theil, Applied Economic Forecasting (North-Holland, Amsterdam, 1996)Google Scholar
  37. 37.
    P. Tino, C. Schittenkopt, G. Dorner, Financial volatility trading using recurrent neural networks. IEEE Trans. Neural Network 12(4), 865–874 (2001)Google Scholar
  38. 38.
    F.M. Tseng, H.C. Yu, G.H. Tzeng, Combining neural network model with seasonal time series ARIMA model. Technol. Forecast. Soc. Change 69, 71–87 (2002)Google Scholar
  39. 39.
    Y.-H. Wang, Nonlinear neural network forecasting model for stock index option price: Hybrid GJR-GARCH approach. Expert Syst. Appl. 36(1), 564–570 (2009)Google Scholar
  40. 40.
    G.P. Zhang, Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159–175 (2003)Google Scholar
  41. 41.
    R.L. Winkler, Combining forecasts: A philosophical basis and some current issues. Int. J. Forecast. 5, 605–609 (1989)Google Scholar
  42. 42.
    G.P. Zhang, M. Qi, Neural network forecasting for seasonal and trend time series. Eur. J. Oper. Res. 160(2), 501–514 (2005)Google Scholar

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  • Christian L. Dunis
    • 1
    Email author
  • Jason Laws
    • 2
  • Andreas Karathanasopoulos
    • 3
  1. 1.Liverpool John Moores UniversityLiverpoolUK
  2. 2.University of Liverpool Management SchoolLiverpoolUK
  3. 3.London Metropolitan UniversityLondonUK

Personalised recommendations