Lancaster EPrints

Computational intelligence methods for financial time series modeling

Pavlidis, Nicos and Tasoulis, Dimitrios K and Plagianakos, Vassilis P. and Vrahatis, Michael N. (2006) Computational intelligence methods for financial time series modeling. International Journal of Bifurcation and Chaos, 16 (7). 2053–2062. ISSN 0218-1274

Full text not available from this repository.

Abstract

In this paper, the combination of unsupervised clustering algorithms with feedforward neural networks in exchange rate time series forecasting is studied. Unsupervised clustering algorithms have the desirable property of deciding on the number of partitions required to accurately segment the input space during the clustering process, thus relieving the user from making this ad hoc choice. Combining this input space partitioning methodology with feedforward neural networks acting as local predictors for each identified cluster helps alleviate the problem of nonstationarity frequently encountered in real-life applications. An improvement in the one-step-ahead forecasting accuracy was achieved compared to a global feedforward neural network model for the time series of the exchange rate of the German Mark to the US Dollar.

Item Type: Article
Journal or Publication Title: International Journal of Bifurcation and Chaos
Uncontrolled Keywords: Time series modeling and prediction ; unsupervised clustering ; Neural networks
Subjects:
Departments: Lancaster University Management School > Management Science
ID Code: 50915
Deposited By: ep_importer_pure
Deposited On: 09 Nov 2011 13:45
Refereed?: Yes
Published?: Published
Last Modified: 26 Jul 2012 19:45
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/50915

Actions (login required)

View Item