Can currency-based risk factors help forecast exchange rates?

This paper examines time-series predictability of bilateral exchange rates from linear factor models that utilize unconditional and conditional expectations of three currency-based risk factors. Exploiting a comprehensive set of statistical criteria, we find that all versions of the linear factor mo...

Full description

Bibliographic Details
Main Authors: Ahmed, Shamim, Liu, Xiaoquan, Valente, Giorgio
Format: Article
Language:English
Published: Elsevier 2015
Subjects:
Online Access:https://eprints.nottingham.ac.uk/36949/
_version_ 1848795364622073856
author Ahmed, Shamim
Liu, Xiaoquan
Valente, Giorgio
author_facet Ahmed, Shamim
Liu, Xiaoquan
Valente, Giorgio
author_sort Ahmed, Shamim
building Nottingham Research Data Repository
collection Online Access
description This paper examines time-series predictability of bilateral exchange rates from linear factor models that utilize unconditional and conditional expectations of three currency-based risk factors. Exploiting a comprehensive set of statistical criteria, we find that all versions of the linear factor models largely fail to outperform the benchmark of random walk with drift model in the out-of-sample forecasting of monthly exchange rate returns. This holds true for individual currencies and currency portfolios formed on forward discounts. We also show that the information embedded in the currency-based risk factors does not generate systematic economic value to investors.
first_indexed 2025-11-14T19:30:55Z
format Article
id nottingham-36949
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T19:30:55Z
publishDate 2015
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling nottingham-369492017-10-18T18:14:32Z https://eprints.nottingham.ac.uk/36949/ Can currency-based risk factors help forecast exchange rates? Ahmed, Shamim Liu, Xiaoquan Valente, Giorgio This paper examines time-series predictability of bilateral exchange rates from linear factor models that utilize unconditional and conditional expectations of three currency-based risk factors. Exploiting a comprehensive set of statistical criteria, we find that all versions of the linear factor models largely fail to outperform the benchmark of random walk with drift model in the out-of-sample forecasting of monthly exchange rate returns. This holds true for individual currencies and currency portfolios formed on forward discounts. We also show that the information embedded in the currency-based risk factors does not generate systematic economic value to investors. Elsevier 2015-09-21 Article PeerReviewed application/pdf en cc_by_nc_nd https://eprints.nottingham.ac.uk/36949/1/FX%20Forecasting.pdf Ahmed, Shamim, Liu, Xiaoquan and Valente, Giorgio (2015) Can currency-based risk factors help forecast exchange rates? International Journal of Forecasting, 32 (1). pp. 75-97. ISSN 0169-2070 Exchange rates; Out-of-sample predictability; Economic value; Time series; Econometric models http://www.sciencedirect.com/science/article/pii/S016920701500062X doi:10.1016/j.ijforecast.2015.01.010 doi:10.1016/j.ijforecast.2015.01.010
spellingShingle Exchange rates; Out-of-sample predictability; Economic value; Time series; Econometric models
Ahmed, Shamim
Liu, Xiaoquan
Valente, Giorgio
Can currency-based risk factors help forecast exchange rates?
title Can currency-based risk factors help forecast exchange rates?
title_full Can currency-based risk factors help forecast exchange rates?
title_fullStr Can currency-based risk factors help forecast exchange rates?
title_full_unstemmed Can currency-based risk factors help forecast exchange rates?
title_short Can currency-based risk factors help forecast exchange rates?
title_sort can currency-based risk factors help forecast exchange rates?
topic Exchange rates; Out-of-sample predictability; Economic value; Time series; Econometric models
url https://eprints.nottingham.ac.uk/36949/
https://eprints.nottingham.ac.uk/36949/
https://eprints.nottingham.ac.uk/36949/