Title: Leveraging artificial neural networks for hedging foreign investments in emerging markets: a large-scale empirical study
Author: Smit Suman
Address: Richard Ivey School of Business, University of Western Ontario, 1255 Western Rd., London, ON N6G 0N1, Canada
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.
Keywords: emerging markets; foreign exchange forecasting; neural networks.
Int. J. of Electronic Finance, 2016 Vol.9, No.1, pp.42 - 62
Submission date: 06 Jul 2016
Date of acceptance: 22 Oct 2016
Available online: 07 Apr 2017