How is machine learning useful for macroeconomic forecasting?

Philippe Goulet Coulombe, Maxime Leroux, Dalibor Stevanovic and Stéphane Surprenant

Journal of Applied Econometrics, 2022, vol. 37, issue 5, 920-964

Abstract: We move beyond Is Machine Learning Useful for Macroeconomic Forecasting? by adding the how. The current forecasting literature has focused on matching specific variables and horizons with a particularly successful algorithm. To the contrary, we study the usefulness of the underlying features driving ML gains over standard macroeconometric methods. We distinguish four so‐called features (nonlinearities, regularization, cross‐validation, and alternative loss function) and study their behavior in both the data‐rich and data‐poor environments. To do so, we design experiments that allow to identify the “treatment” effects of interest. We conclude that (i) nonlinearity is the true game changer for macroeconomic prediction, (ii) the standard factor model remains the best regularization, (iii) K‐fold cross‐validation is the best practice, and (iv) the L2$$ {L}_2 $$ is preferred to the ϵ¯$$ \overline{\epsilon} $$‐insensitive in‐sample loss. The forecasting gains of nonlinear techniques are associated with high macroeconomic uncertainty, financial stress and housing bubble bursts. Furthermore, ML nonlinearities are helpful when considering density forecasts.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (45)

Downloads: (external link)
https://doi.org/10.1002/jae.2910

Related works:
Working Paper: How is Machine Learning Useful for Macroeconomic Forecasting? (2020)
Working Paper: How is Machine Learning Useful for Macroeconomic Forecasting? (2020)
Working Paper: How is Machine Learning Useful for Macroeconomic Forecasting? (2019)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wly:japmet:v:37:y:2022:i:5:p:920-964

Ordering information: This journal article can be ordered from
http://www3.intersci ... e.jsp?issn=0883-7252

Access Statistics for this article

Journal of Applied Econometrics is currently edited by M. Hashem Pesaran

More articles in Journal of Applied Econometrics from John Wiley & Sons, Ltd.
Bibliographic data for series maintained by Wiley Content Delivery ().