Home > Research > Publications & Outputs > Financial forecasting through unsupervised clus...

Research

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Financial forecasting through unsupervised clustering and evolutionary trained neural networks

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Financial forecasting through unsupervised clustering and evolutionary trained neural networks. / Pavlidis, Nicos; Tasoulis, DK; Vrahatis, Michael N.
IEEE Congress on Evolutionary Computation. Vol. 4 IEEE, 2003. p. 2314-2321.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Pavlidis, N, Tasoulis, DK & Vrahatis, MN 2003, Financial forecasting through unsupervised clustering and evolutionary trained neural networks. in IEEE Congress on Evolutionary Computation. vol. 4, IEEE, pp. 2314-2321. https://doi.org/10.1109/CEC.2003.1299377

APA

Pavlidis, N., Tasoulis, DK., & Vrahatis, M. N. (2003). Financial forecasting through unsupervised clustering and evolutionary trained neural networks. In IEEE Congress on Evolutionary Computation (Vol. 4, pp. 2314-2321). IEEE. https://doi.org/10.1109/CEC.2003.1299377

Vancouver

Pavlidis N, Tasoulis DK, Vrahatis MN. Financial forecasting through unsupervised clustering and evolutionary trained neural networks. In IEEE Congress on Evolutionary Computation. Vol. 4. IEEE. 2003. p. 2314-2321 doi: 10.1109/CEC.2003.1299377

Author

Pavlidis, Nicos ; Tasoulis, DK ; Vrahatis, Michael N. / Financial forecasting through unsupervised clustering and evolutionary trained neural networks. IEEE Congress on Evolutionary Computation. Vol. 4 IEEE, 2003. pp. 2314-2321

Bibtex

@inproceedings{ea182287662c42db8c741753f9f7ca7c,
title = "Financial forecasting through unsupervised clustering and evolutionary trained neural networks",
abstract = "We present a time series forecasting methodology and applies it to generate one-step-ahead predictions for two daily foreign exchange spot rate time series. The methodology draws from the disciplines of chaotic time series analysis, clustering, artificial neural networks and evolutionary computation. In brief, clustering is applied to identify neighborhoods in the reconstructed state space of the system; and subsequently neural networks are trained to model the dynamics of each neighborhood separately. The results obtained through this approach are promising.",
author = "Nicos Pavlidis and DK Tasoulis and Vrahatis, {Michael N.}",
year = "2003",
doi = "10.1109/CEC.2003.1299377",
language = "English",
isbn = "0-7803-7804-0 ",
volume = "4",
pages = "2314--2321",
booktitle = "IEEE Congress on Evolutionary Computation",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Financial forecasting through unsupervised clustering and evolutionary trained neural networks

AU - Pavlidis, Nicos

AU - Tasoulis, DK

AU - Vrahatis, Michael N.

PY - 2003

Y1 - 2003

N2 - We present a time series forecasting methodology and applies it to generate one-step-ahead predictions for two daily foreign exchange spot rate time series. The methodology draws from the disciplines of chaotic time series analysis, clustering, artificial neural networks and evolutionary computation. In brief, clustering is applied to identify neighborhoods in the reconstructed state space of the system; and subsequently neural networks are trained to model the dynamics of each neighborhood separately. The results obtained through this approach are promising.

AB - We present a time series forecasting methodology and applies it to generate one-step-ahead predictions for two daily foreign exchange spot rate time series. The methodology draws from the disciplines of chaotic time series analysis, clustering, artificial neural networks and evolutionary computation. In brief, clustering is applied to identify neighborhoods in the reconstructed state space of the system; and subsequently neural networks are trained to model the dynamics of each neighborhood separately. The results obtained through this approach are promising.

U2 - 10.1109/CEC.2003.1299377

DO - 10.1109/CEC.2003.1299377

M3 - Conference contribution/Paper

SN - 0-7803-7804-0

VL - 4

SP - 2314

EP - 2321

BT - IEEE Congress on Evolutionary Computation

PB - IEEE

ER -