A Machine Learning Approach to Forecasting Carry Trade Returns
Xiao Wang, Xiao Xie, Yihua Chen & Borui Zhao (2021) A machine learning approach to forecasting carry trade returns, Applied Economics Letters, https://doi.org/10.1080/13504851.2021.1918624
15 Pages Posted: 3 Nov 2020 Last revised: 4 Oct 2021
Date Written: August 23, 2020
Abstract
Carry trade refers to a risky arbitrage in interest rate differentials between two currencies. Persistent excess carry trade returns pose a challenge to foreign exchange market efficiency. Using a data set of ten currencies between 1990 and 2017, we find: (i) a machine learning model, long short-term memory (LSTM) networks, forecast carry trade returns better than linear and threshold regressions based on economic fundamentals; and (ii) excess carry trade returns deteriorate after the 2007--2008 global financial crisis in LSTM networks and other model forecasts, indicating that the uncovered interest rate parity may still hold in the long run.
Keywords: carry trade, uncovered interest rate parity, machine learning, long short-term memory networks
JEL Classification: C45, F21, F31, F37
Suggested Citation: Suggested Citation