Nonlinear time series and neural-network models of exchange rates between the US dollar and major currencies

David E. Allen, Michael McAleer, Shelton Peiris, Abhay Singh

Research output: Contribution to journal › Article › Research › peer-review

Abstract

This paper features an analysis of major currency exchange rate movements in relation to the US dollar, as constituted in US dollar terms. Euro, British pound, Chinese yuan, and Japanese yen are modelled using a variety of non-linear models, including smooth transition regression models, logistic smooth transition regressions models, threshold autoregressive models, nonlinear autoregressive models, and additive nonlinear autoregressive models, plus Neural Network models. The models are evaluated on the basis of error metrics for twenty day out-of-sample forecasts using the mean average percentage errors (MAPE). The results suggest that there is no dominating class of time series models, and the different currency pairs relationships with the US dollar are captured best by neural net regression models, over the ten year sample of daily exchange rate returns data, from August 2005 to August 2015.
LanguageEnglish
Article number7
Number of pages14
JournalRisks
Volume4
Issue number1
DOIs
Publication statusPublished - 16 Mar 2016
Externally publishedYes

Fingerprint

Nonlinear time series
Regression model
Currency
Neural networks
Exchange rates
Network model
Autoregressive model
Smooth transition regression
Out-of-sample forecasting
Threshold autoregressive model
Neural nets
Logistics
Time series models
Exchange rate returns

Bibliographical note

Copyright 2016 by the authors; licensee MDPI, Basel, Switzerland. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

  • non linear models
  • time series
  • non-parametric
  • smooth-transition regression models
  • neural networks
  • GMDH shell

Cite this

Allen, David E. ; McAleer, Michael ; Peiris, Shelton ; Singh, Abhay. / Nonlinear time series and neural-network models of exchange rates between the US dollar and major currencies. In: Risks. 2016 ; Vol. 4, No. 1.
@article{d5f35213f55e4d9aa84ea46b7c0db28e,
title = "Nonlinear time series and neural-network models of exchange rates between the US dollar and major currencies",
abstract = "This paper features an analysis of major currency exchange rate movements in relation to the US dollar, as constituted in US dollar terms. Euro, British pound, Chinese yuan, and Japanese yen are modelled using a variety of non-linear models, including smooth transition regression models, logistic smooth transition regressions models, threshold autoregressive models, nonlinear autoregressive models, and additive nonlinear autoregressive models, plus Neural Network models. The models are evaluated on the basis of error metrics for twenty day out-of-sample forecasts using the mean average percentage errors (MAPE). The results suggest that there is no dominating class of time series models, and the different currency pairs relationships with the US dollar are captured best by neural net regression models, over the ten year sample of daily exchange rate returns data, from August 2005 to August 2015.",
keywords = "non linear models, time series, non-parametric, smooth-transition regression models, neural networks, GMDH shell",
author = "Allen, {David E.} and Michael McAleer and Shelton Peiris and Abhay Singh",
note = "Copyright 2016 by the authors; licensee MDPI, Basel, Switzerland. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",
year = "2016",
month = "3",
day = "16",
doi = "10.3390/risks4010007",
language = "English",
volume = "4",
journal = "Risks",
issn = "2227-9091",
publisher = "MDPI AG",
number = "1",

}

Allen, DE, McAleer, M, Peiris, S & Singh, A 2016, 'Nonlinear time series and neural-network models of exchange rates between the US dollar and major currencies', Risks, vol. 4, no. 1, 7. https://doi.org/10.3390/risks4010007

Nonlinear time series and neural-network models of exchange rates between the US dollar and major currencies. / Allen, David E.; McAleer, Michael; Peiris, Shelton; Singh, Abhay.

In: Risks, Vol. 4, No. 1, 7, 16.03.2016.

Research output: Contribution to journal › Article › Research › peer-review

TY - JOUR

T1 - Nonlinear time series and neural-network models of exchange rates between the US dollar and major currencies

AU - Allen, David E.

AU - McAleer, Michael

AU - Peiris, Shelton

AU - Singh, Abhay

N1 - Copyright 2016 by the authors; licensee MDPI, Basel, Switzerland. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2016/3/16

Y1 - 2016/3/16

N2 - This paper features an analysis of major currency exchange rate movements in relation to the US dollar, as constituted in US dollar terms. Euro, British pound, Chinese yuan, and Japanese yen are modelled using a variety of non-linear models, including smooth transition regression models, logistic smooth transition regressions models, threshold autoregressive models, nonlinear autoregressive models, and additive nonlinear autoregressive models, plus Neural Network models. The models are evaluated on the basis of error metrics for twenty day out-of-sample forecasts using the mean average percentage errors (MAPE). The results suggest that there is no dominating class of time series models, and the different currency pairs relationships with the US dollar are captured best by neural net regression models, over the ten year sample of daily exchange rate returns data, from August 2005 to August 2015.

AB - This paper features an analysis of major currency exchange rate movements in relation to the US dollar, as constituted in US dollar terms. Euro, British pound, Chinese yuan, and Japanese yen are modelled using a variety of non-linear models, including smooth transition regression models, logistic smooth transition regressions models, threshold autoregressive models, nonlinear autoregressive models, and additive nonlinear autoregressive models, plus Neural Network models. The models are evaluated on the basis of error metrics for twenty day out-of-sample forecasts using the mean average percentage errors (MAPE). The results suggest that there is no dominating class of time series models, and the different currency pairs relationships with the US dollar are captured best by neural net regression models, over the ten year sample of daily exchange rate returns data, from August 2005 to August 2015.

KW - non linear models

KW - time series

KW - non-parametric

KW - smooth-transition regression models

KW - neural networks

KW - GMDH shell

U2 - 10.3390/risks4010007

DO - 10.3390/risks4010007

M3 - Article

VL - 4

JO - Risks

T2 - Risks

JF - Risks

SN - 2227-9091

IS - 1

M1 - 7

ER -

Allen DE, McAleer M, Peiris S, Singh A. Nonlinear time series and neural-network models of exchange rates between the US dollar and major currencies. Risks. 2016 Mar 16;4(1). 7. https://doi.org/10.3390/risks4010007

Access to Document