Economic Fundamentals and Short-Run Exchange Rate Prediction: A Machine Learning Perspective

50 Pages Posted: 27 Sep 2019 Last revised: 19 Dec 2023

See all articles by Ilias Filippou

Ilias Filippou

Washington University in St. Louis - John M. Olin Business School

David Rapach

Research Department, Federal Reserve Bank of Atlanta; Washington University in St. Louis

Mark P. Taylor

Washington University in St. Louis - John M. Olin Business School; Centre for Economic Policy Research (CEPR); Brookings Institution

Guofu Zhou

Washington University in St. Louis - John M. Olin Business School

Date Written: December 12, 2023

Abstract

This paper establishes the short-run, out-of-sample predictability of monthly exchange rates based on fundamental predictors capturing country characteristics, global variables, and their interactions. Previous work has shown evidence of long-horizon but not short-horizon predictability due to inadequately capturing time variation and non-linearity and using only a small set of fundamental variables. By employing machine learning techniques that allow for time variation, non-linearity, and a broad menu of economic fundamentals, we are able to consistently and significantly outperform a random walk benchmark. Stronger predictability is shown during recessions and crises, consistent with heterogeneous agent models in which fundamental and non-fundamental, technical traders interact. The fundamental forecasts are also economically valuable, enhancing the performance of foreign currency portfolios, particularly post the Global Financial Crisis when carry trade portfolio profitability declines. From an asset pricing perspective, we also show that machine learning forecasts provide a plausible depiction of the conditional price of currency risk.

Keywords: Economic fundamentals, Exchange rate forecasting, Panel predictive regression, Elastic net, Deep neural network, Asset allocation, Conditional price of risk

JEL Classification: C45, F31, F37, G11, G12, G15

Suggested Citation

Filippou, Ilias and Rapach, David and Taylor, Mark P. and Zhou, Guofu, Economic Fundamentals and Short-Run Exchange Rate Prediction: A Machine Learning Perspective (December 12, 2023). Available at SSRN: https://ssrn.com/abstract=3455713 or http://dx.doi.org/10.2139/ssrn.3455713

Ilias Filippou

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

David Rapach (Contact Author)

Research Department, Federal Reserve Bank of Atlanta ( email )

1000 Peachtree Street N.E.
Atlanta, GA 30309-4470
United States

Washington University in St. Louis ( email )

One Brookings Drive
Campus Box 1133
St. Louis, MO 63130-4899
United States

HOME PAGE: http://https://sites.google.com/slu.edu/daverapach

Mark P. Taylor

Washington University in St. Louis - John M. Olin Business School ( email )

One Brookings Drive
Campus Box 1156
St. Louis, MO 63130-4899
United States

Centre for Economic Policy Research (CEPR)

London
United Kingdom

Brookings Institution ( email )

1775 Massachusetts Ave, NW
Washington, DC 20036
United States

Guofu Zhou

Washington University in St. Louis - John M. Olin Business School ( email )

Washington University
Campus Box 1133
St. Louis, MO 63130-4899
United States
314-935-6384 (Phone)
314-658-6359 (Fax)

HOME PAGE: http://apps.olin.wustl.edu/faculty/zhou/

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,578
Abstract Views
5,219
Rank
22,180
PlumX Metrics