Can machine learning catch the COVID-19 recession?

Publication date: 23 Jun 2021 | Publication type: National Institute Economic Review | External Author(s): Coulombe, P G; Marcellino, M; Stevanovic, D | JEL Classification: C53; C55; E37 | Journal: National Institute Economic Review Issue 256 | Publisher: Cambridge University Press

Based on evidence gathered from a newly built large macroeconomic dataset (MD) for the UK, labelled UK-MD and comparable to similar datasets for the United States and Canada, it seems the most promising avenue for forecasting during the pandemic is to allow for general forms of nonlinearity by using machine learning (ML) methods. But not all nonlinear ML methods are alike. For instance, some do not allow to extrapolate (like regular trees and forests) and some do (when complemented with linear dynamic components). This and other crucial aspects of ML-based forecasting in unprecedented times are studied in an extensive pseudo-out-of-sample exercise.

Keyword tags: 
machine learning
big data
forecasting
COVID-19