Chaos-based support vector regressions for exchange rate forecasting

Shian-Chang Huang, Pei Ju Chuang, Cheng Feng Wu, Hiuen Jiun Lai

Research output: Contribution to journalArticle

50 Citations (Scopus)

Abstract

This study implements a chaos-based model to predict the foreign exchange rates. In the first stage, the delay coordinate embedding is used to reconstruct the unobserved phase space (or state space) of the exchange rate dynamics. The phase space exhibits the inherent essential characteristic of the exchangerate and is suitable for financial modeling and forecasting. In the second stage, kernel predictors such as support vector machines (SVMs) are constructed for forecasting. Compared with traditional neural networks, pure SVMs or chaos-based neural network models, the proposed model performs best. The rootmean- squared forecasting errors are significantly reduced.

Original languageEnglish
Pages (from-to)8590-8598
Number of pages9
JournalExpert Systems with Applications
Volume37
Issue number12
DOIs
Publication statusPublished - 2010 Jan 1

Fingerprint

Chaos theory
Support vector machines
Neural networks

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Huang, Shian-Chang ; Chuang, Pei Ju ; Wu, Cheng Feng ; Lai, Hiuen Jiun. / Chaos-based support vector regressions for exchange rate forecasting. In: Expert Systems with Applications. 2010 ; Vol. 37, No. 12. pp. 8590-8598.
@article{3be53a547ae743898b20a82aee1ec161,
title = "Chaos-based support vector regressions for exchange rate forecasting",
abstract = "This study implements a chaos-based model to predict the foreign exchange rates. In the first stage, the delay coordinate embedding is used to reconstruct the unobserved phase space (or state space) of the exchange rate dynamics. The phase space exhibits the inherent essential characteristic of the exchangerate and is suitable for financial modeling and forecasting. In the second stage, kernel predictors such as support vector machines (SVMs) are constructed for forecasting. Compared with traditional neural networks, pure SVMs or chaos-based neural network models, the proposed model performs best. The rootmean- squared forecasting errors are significantly reduced.",
author = "Shian-Chang Huang and Chuang, {Pei Ju} and Wu, {Cheng Feng} and Lai, {Hiuen Jiun}",
year = "2010",
month = "1",
day = "1",
doi = "10.1016/j.eswa.2010.06.001",
language = "English",
volume = "37",
pages = "8590--8598",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "12",

}

Chaos-based support vector regressions for exchange rate forecasting. / Huang, Shian-Chang; Chuang, Pei Ju; Wu, Cheng Feng; Lai, Hiuen Jiun.

In: Expert Systems with Applications, Vol. 37, No. 12, 01.01.2010, p. 8590-8598.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Chaos-based support vector regressions for exchange rate forecasting

AU - Huang, Shian-Chang

AU - Chuang, Pei Ju

AU - Wu, Cheng Feng

AU - Lai, Hiuen Jiun

PY - 2010/1/1

Y1 - 2010/1/1

N2 - This study implements a chaos-based model to predict the foreign exchange rates. In the first stage, the delay coordinate embedding is used to reconstruct the unobserved phase space (or state space) of the exchange rate dynamics. The phase space exhibits the inherent essential characteristic of the exchangerate and is suitable for financial modeling and forecasting. In the second stage, kernel predictors such as support vector machines (SVMs) are constructed for forecasting. Compared with traditional neural networks, pure SVMs or chaos-based neural network models, the proposed model performs best. The rootmean- squared forecasting errors are significantly reduced.

AB - This study implements a chaos-based model to predict the foreign exchange rates. In the first stage, the delay coordinate embedding is used to reconstruct the unobserved phase space (or state space) of the exchange rate dynamics. The phase space exhibits the inherent essential characteristic of the exchangerate and is suitable for financial modeling and forecasting. In the second stage, kernel predictors such as support vector machines (SVMs) are constructed for forecasting. Compared with traditional neural networks, pure SVMs or chaos-based neural network models, the proposed model performs best. The rootmean- squared forecasting errors are significantly reduced.

UR - http://www.scopus.com/inward/record.url?scp=77957853038&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957853038&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2010.06.001

DO - 10.1016/j.eswa.2010.06.001

M3 - Article

VL - 37

SP - 8590

EP - 8598

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 12

ER -