Fundamentals and exchange rate forecastability with simple machine learning methods

Christophe Amat (1) , Tomasz Michalski (1) , Gilles Stoltz (1)

1 GREGH - Groupement de Recherche et d'Etudes en Gestion à HEC

Using methods from machine learning we show that fundamentals from simple exchange rate models (PPP or UIRP) or Taylor-rule based models lead to improved exchange rate forecasts for major currencies over the floating period era 1973--2014 at a 1-month forecast horizon which beat the no-change forecast. Fundamentals thus contain useful information and exchange rates are forecastable even for short horizons. Such conclusions cannot be obtained when using rolling or recursive OLS regressions as used in the literature. The methods we use -- sequential ridge regression and the exponentially weighted average strategy, both with discount factors -- do not estimate an underlying model but combine the fundamentals to directly output forecasts.

Keywords: uncovered interest rate parity; monetary exchange rate models; purchasing power parity; machine learning; forecasting; exchange rates; Taylor-rule exchange rate models

Domains: Economics and Finance; Methods and statistics

Christophe Amat, Tomasz Michalski, Gilles Stoltz. Fundamentals and exchange rate forecastability with simple machine learning methods. 2018. ⟨halshs-01003914v6⟩