Nowcasting GDP using machine-learning algorithms: A real-time assessment

Adam Richardson*, Thomas van Florenstein Mulder, Tuğrul Vehbi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

56 Citations (Scopus)

Abstract

Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand.

Original languageEnglish
Pages (from-to)941-948
Number of pages8
JournalInternational Journal of Forecasting
Volume37
Issue number2
DOIs
Publication statusPublished - 1 Apr 2021
Externally publishedYes

Fingerprint

Dive into the research topics of 'Nowcasting GDP using machine-learning algorithms: A real-time assessment'. Together they form a unique fingerprint.

Cite this