Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/322096 
Year of Publication: 
2025
Series/Report no.: 
ECB Working Paper No. 3063
Publisher: 
European Central Bank (ECB), Frankfurt a. M.
Abstract: 
This study involves tasking ChatGPT with classifying an "activity sentiment score" based on PMI news releases. It explores the predictive power of this score for euro area GDP nowcasting. We find that the PMI text scores enhance GDP nowcasts beyond what is embedded in ECB/Eurosystem Staff projections and Eurostat's first GDP estimate. The ChatGPT-derived activity score retains its significance in regressions that also include the composite output PMI diffusion index. GDP nowcasts are significantly enhanced with PMI text scores even when accounting for methodological variations, excluding extraordinary economic events like the pandemic, and for different GDP growth quantiles. However, the forecast gains from the enhancement of GDP nowcasts with ChatGPT scores are time dependent, varying by calendar years. Sizeable forecast gains of on average about 20% were obtained apart from the two most recent years due to exceptionally low forecast errors of the two benchmarks, especially the first GDP estimate.
Subjects: 
Chat Generative Pre-training Transformer
text analysis
zero-shot sentiment analysis
Purchasing Managers' Index (PMI)
nowcasting GDP
JEL: 
C8
E32
C22
Persistent Identifier of the first edition: 
ISBN: 
978-92-899-7239-0
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.