Home > Research > Publications & Outputs > Computational intelligence methods for financia...
View graph of relations

Computational intelligence methods for financial time series modeling

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Computational intelligence methods for financial time series modeling. / Pavlidis, Nicos; Tasoulis, Dimitrios K; Plagianakos, Vassilis P. et al.

In: International Journal of Bifurcation and Chaos, Vol. 16, No. 7, 07.2006, p. 2053–2062 .

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Pavlidis, N, Tasoulis, DK, Plagianakos, VP & Vrahatis, MN 2006, 'Computational intelligence methods for financial time series modeling', International Journal of Bifurcation and Chaos, vol. 16, no. 7, pp. 2053–2062 . https://doi.org/10.1142/S0218127406015891

APA

Pavlidis, N., Tasoulis, D. K., Plagianakos, V. P., & Vrahatis, M. N. (2006). Computational intelligence methods for financial time series modeling. International Journal of Bifurcation and Chaos, 16(7), 2053–2062 . https://doi.org/10.1142/S0218127406015891

Vancouver

Pavlidis N, Tasoulis DK, Plagianakos VP, Vrahatis MN. Computational intelligence methods for financial time series modeling. International Journal of Bifurcation and Chaos. 2006 Jul;16(7):2053–2062 . doi: 10.1142/S0218127406015891

Author

Pavlidis, Nicos ; Tasoulis, Dimitrios K ; Plagianakos, Vassilis P. et al. / Computational intelligence methods for financial time series modeling. In: International Journal of Bifurcation and Chaos. 2006 ; Vol. 16, No. 7. pp. 2053–2062 .

Bibtex

@article{76b4df7ac5af406d92b6cc62f2bbab35,
title = "Computational intelligence methods for financial time series modeling",
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.",
keywords = "Time series modeling and prediction, unsupervised clustering, Neural networks",
author = "Nicos Pavlidis and Tasoulis, {Dimitrios K} and Plagianakos, {Vassilis P.} and Vrahatis, {Michael N.}",
year = "2006",
month = jul,
doi = "10.1142/S0218127406015891",
language = "English",
volume = "16",
pages = "2053–2062 ",
journal = "International Journal of Bifurcation and Chaos",
issn = "0218-1274",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "7",

}

RIS

TY - JOUR

T1 - Computational intelligence methods for financial time series modeling

AU - Pavlidis, Nicos

AU - Tasoulis, Dimitrios K

AU - Plagianakos, Vassilis P.

AU - Vrahatis, Michael N.

PY - 2006/7

Y1 - 2006/7

N2 - 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.

AB - 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.

KW - Time series modeling and prediction

KW - unsupervised clustering

KW - Neural networks

U2 - 10.1142/S0218127406015891

DO - 10.1142/S0218127406015891

M3 - Journal article

VL - 16

SP - 2053

EP - 2062

JO - International Journal of Bifurcation and Chaos

JF - International Journal of Bifurcation and Chaos

SN - 0218-1274

IS - 7

ER -