Leading edge forecasting techniques for exchange rate prediction

Ian T. Nabney, Christian Dunis, Richard Dallaway, Swee Leong, Wendy Redshaw

Research output: Contribution to journalArticle

Abstract

This paper describes how modern machine learning techniques can be used in conjunction with statistical methods to forecast short term movements in exchange rates, producing models suitable for use in trading. It compares the results achieved by two different techniques, and shows how they can be used in a complementary fashion. The paper draws on experience of both inter- and intra-day forecasting taken from earlier studies conducted by Logica and Chemical Bank Quantitative Research and Trading (QRT) group's experience in developing trading models.
Original languageEnglish
Pages (from-to)311-323
Number of pages13
JournalEuropean Journal of Finance
Volume1
Issue number4
DOIs
Publication statusPublished - 4 Dec 1995

Fingerprint

Prediction
Exchange rates
Statistical methods
Quantitative research
Machine learning

Keywords

  • machine learning technique
  • leading-edge forecasting
  • rule induction
  • neural networks

Cite this

Nabney, I. T., Dunis, C., Dallaway, R., Leong, S., & Redshaw, W. (1995). Leading edge forecasting techniques for exchange rate prediction. European Journal of Finance, 1(4), 311-323. https://doi.org/10.1080/13518479500000022
Nabney, Ian T. ; Dunis, Christian ; Dallaway, Richard ; Leong, Swee ; Redshaw, Wendy. / Leading edge forecasting techniques for exchange rate prediction. In: European Journal of Finance. 1995 ; Vol. 1, No. 4. pp. 311-323.
@article{ba3ed4b37af94305b5392f29353c728b,
title = "Leading edge forecasting techniques for exchange rate prediction",
abstract = "This paper describes how modern machine learning techniques can be used in conjunction with statistical methods to forecast short term movements in exchange rates, producing models suitable for use in trading. It compares the results achieved by two different techniques, and shows how they can be used in a complementary fashion. The paper draws on experience of both inter- and intra-day forecasting taken from earlier studies conducted by Logica and Chemical Bank Quantitative Research and Trading (QRT) group's experience in developing trading models.",
keywords = "machine learning technique, leading-edge forecasting, rule induction, neural networks",
author = "Nabney, {Ian T.} and Christian Dunis and Richard Dallaway and Swee Leong and Wendy Redshaw",
year = "1995",
month = "12",
day = "4",
doi = "10.1080/13518479500000022",
language = "English",
volume = "1",
pages = "311--323",
journal = "European Journal of Finance",
issn = "1351-847X",
publisher = "Routledge",
number = "4",

}

Nabney, IT, Dunis, C, Dallaway, R, Leong, S & Redshaw, W 1995, 'Leading edge forecasting techniques for exchange rate prediction', European Journal of Finance, vol. 1, no. 4, pp. 311-323. https://doi.org/10.1080/13518479500000022

Leading edge forecasting techniques for exchange rate prediction. / Nabney, Ian T.; Dunis, Christian; Dallaway, Richard; Leong, Swee; Redshaw, Wendy.

In: European Journal of Finance, Vol. 1, No. 4, 04.12.1995, p. 311-323.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Leading edge forecasting techniques for exchange rate prediction

AU - Nabney, Ian T.

AU - Dunis, Christian

AU - Dallaway, Richard

AU - Leong, Swee

AU - Redshaw, Wendy

PY - 1995/12/4

Y1 - 1995/12/4

N2 - This paper describes how modern machine learning techniques can be used in conjunction with statistical methods to forecast short term movements in exchange rates, producing models suitable for use in trading. It compares the results achieved by two different techniques, and shows how they can be used in a complementary fashion. The paper draws on experience of both inter- and intra-day forecasting taken from earlier studies conducted by Logica and Chemical Bank Quantitative Research and Trading (QRT) group's experience in developing trading models.

AB - This paper describes how modern machine learning techniques can be used in conjunction with statistical methods to forecast short term movements in exchange rates, producing models suitable for use in trading. It compares the results achieved by two different techniques, and shows how they can be used in a complementary fashion. The paper draws on experience of both inter- and intra-day forecasting taken from earlier studies conducted by Logica and Chemical Bank Quantitative Research and Trading (QRT) group's experience in developing trading models.

KW - machine learning technique

KW - leading-edge forecasting

KW - rule induction

KW - neural networks

UR - https://www.tandfonline.com/doi/abs/10.1080/13518479500000022

U2 - 10.1080/13518479500000022

DO - 10.1080/13518479500000022

M3 - Article

VL - 1

SP - 311

EP - 323

JO - European Journal of Finance

JF - European Journal of Finance

SN - 1351-847X

IS - 4

ER -