Benchmarking econometric and machine learning methodologies in nowcasting GDP

Daniel Hopp ()
Additional contact information
Daniel Hopp: UNCTAD

Empirical Economics, 2024, vol. 66, issue 5, No 11, 2247 pages

Abstract: Abstract Nowcasting can play a key role in giving policymakers timelier insight to data published with a significant time lag, such as final GDP figures. Currently, there are a plethora of methodologies and approaches for practitioners to choose from. However, there lacks a comprehensive comparison of these disparate approaches in terms of predictive performance and characteristics. This paper addresses that deficiency by examining the performance of 17 different methodologies in nowcasting US quarterly GDP growth, including all the methods most commonly employed in nowcasting, as well as some of the most popular traditional machine learning approaches. Performance was assessed over a 20-year period, from 2002 to 2022. This span encompassed two crises, the 2008 financial crisis and the COVID crisis, as well as extended tranquil periods. The two best-performing methodologies in the analysis were long short-term memory artificial neural networks (LSTM) and Bayesian vector autoregression (Bayesian VAR). To facilitate further application and testing of each of the examined methodologies, an open-source repository containing boilerplate code that can be applied to different datasets is published alongside the paper, available at: github.com/dhopp1/nowcasting_benchmark

Keywords: Macroeconomic forecasting; Machine learning; Neural networks; Vector autoregression models; Econometric models; GDP; Bayesian methods; ARIMA models (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s00181-023-02515-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
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:spr:empeco:v:66:y:2024:i:5:d:10.1007_s00181-023-02515-6

Ordering information: This journal article can be ordered from
http://www.springer. ... rics/journal/181/PS2

DOI: 10.1007/s00181-023-02515-6

Access Statistics for this article

Empirical Economics is currently edited by Robert M. Kunst, Arthur H.O. van Soest, Bertrand Candelon, Subal C. Kumbhakar and Joakim Westerlund

More articles in Empirical Economics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().