Leveraging artificial neural networks for hedging foreign investments in emerging markets: a large-scale empirical study
by Smit Suman
International Journal of Electronic Finance (IJEF), Vol. 9, No. 1, 2016

Abstract: Our work provides a generalisable assessment of prediction performances of ANN models for predicting currencies of emerging markets. We perform a large-scale empirical study on four emerging markets (i.e. India, China, Brazil and Mexico) and two developed markets (i.e. Australia and Singapore) by leveraging three ANN training algorithms to predict their exchange rates against US Dollar, Euro, British Pound and Japanese Yen. We find that our models successfully predict the emerging and developed market currencies for both next week and the next quarter except in the face of a currency crisis. We also find that the Levenberg-Marquardt model outperforms the other two models in predicting exchange rates. Managers of multinational firms can leverage our findings to determine whether or not to hedge their exchange rate exposure for the next quarter and the level of hedging. Moreover, practitioners trading currency futures can leverage our models to determine when to exit their positions.

Online publication date: Sat, 08-Apr-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Electronic Finance (IJEF):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com