Abstract
In this paper, an extended self-organizing regressive neural network is proposed for multistep forecasting of time series. The main features of this method are building input segments with various lengths for training and the network capable of learning multiple regressive models for forecasting various horizons. The inter dependencies among future points are preserved and this results in all forecasting tasks naturally. Experiments on foreign exchange rates show that the new method significantly improves the performance in multistep forecasting compared to the existing methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Triennial Central Bank Survey of foreign exchange and derivatives market activity in 2013 (2013). http://www.bis.org/publ/rpfx13.htm
Euromoney FX survey 2014 (2014). http://www.euromoney.com/
Tsay, R.S.: Analysis of Financial Time Series. Wiley, New York (2005)
Sorjamaa, A., Hao, J., Reyhani, N., Ji, Y., Lendasse, A.: Methodology for long-term prediction of time series. Neurocomputing 70, 2861–2869 (2007)
Zhang, L., Zhou, W.-D., Chang, P.-C., Yang, J.-W., Li, F.-Z.: Iterated time series prediction with multiple support vector regression models. Neurocomputing 99, 411–422 (2013)
Taieb, S.B., Sorjamaa, A., Bontempi, G.: Multiple-output modeling for multistep-ahead time series forecasting. Neurocomputing 73, 1950–1957 (2010)
Simon, G., Lendasse, A., Cottrell, M., Fort, J.-C., Verleysen, M.: Double quantization of the regressor space for long-term time series prediction: method and proof of stability. Neural Netw. 17, 1169–1181 (2004)
Ouyang, Y., Yin, H.: Time series prediction with a non-causal neural network. In: Proceedings of the IEEE Conference on Computational Intelligence for Financial Engineering & Economics, London, UK, pp. 25–31 (2014)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Giles, C.L., Lawrence, S., Tsoi, A.C.: Noisy time series prediction using recurrent neural networks and grammatical inference. Mach. Learn. 44, 161–183 (2001)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273–297 (1995)
Ni, H., Yin, H.: A self-organising mixture autoregressive network for FX time series modelling and prediction. Neurocomputing 72, 3529–3537 (2009)
Ouyang, Y., Yin, H.: A neural gas mixture autoregressive network for modelling and forecasting FX time series. Neurocomputing 135, 171–179 (2014)
Yin, H.: Self-organising: maps background, theories, extensions and applications. In: Fulcher, J. (ed.) Computational Intelligence: A Compendium, pp. 715–762. Springer, Heidelberg (2008)
Lampinen, J., Oja, E.: Self-organizing maps for spatial and temporal AR models. In: Proceedings of the 6th Scandinavian Conference on Image Analysis, Helsinki, Finland, pp. 120–127 (1989)
De Gooijer, J.G., Hyndman, R.J.: 25 years of time series forecasting. Int. J. Forecast. 22, 443–473 (2006)
Li, D., Han, M., Wang, J.: Chaotic time series prediction based on a novel robust echo state network. IEEE Trans. Neural Netw. Learn. Syst. 23, 787–799 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ouyang, Y., Yin, H. (2015). Multistep Forecast of FX Rates Using an Extended Self-organizing Regressive Neural Network. In: Jackowski, K., Burduk, R., Walkowiak, K., Wozniak, M., Yin, H. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2015. IDEAL 2015. Lecture Notes in Computer Science(), vol 9375. Springer, Cham. https://doi.org/10.1007/978-3-319-24834-9_52
Download citation
DOI: https://doi.org/10.1007/978-3-319-24834-9_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24833-2
Online ISBN: 978-3-319-24834-9
eBook Packages: Computer ScienceComputer Science (R0)