Ask, Think, Predict: LLM-Based Nowcasting of Argentina’s GDP

Facundo Gonzalo Gómez García, Jeremías Ángel Manzano Quiroga and María Sol Bernasconi

No 4806, Asociación Argentina de Economía Política: Working Papers from Asociación Argentina de Economía Política

Abstract: We assess the forecasting performance of Gemini 2.0 Flash Thinking Experimental with Apps for Argentina’s seasonally adjusted quarter-over-quarter real GDP growth over 2021–2024. Using a transparent prompt-engineering protocol, we elicit point forecasts at three horizons and evaluate them in real time against the Central Bank’s Relevamiento de Expectativas de Mercado (REM). Across data vintages, Gemini delivers accuracy comparable to expert consensus—especially at nowcast and one-quarter-ahead horizons—while operating at effectively zero marginal cost. We also document where performance deteriorates (regime shifts and data revisions) and show that simple prompt safeguards improve stability. Overall, general-purpose LLMs can complement conventional workflows by providing competitive short-horizon forecasts with minimal implementation overhead.

JEL-codes: E0 E3 (search for similar items in EconPapers)
Pages: 21 pages
Date: 2025-12
References: Add references at CitEc
Citations:

Downloads: (external link)
https://aaep.org.ar/works/works2025/4806.pdf (application/pdf)

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:aep:anales:4806

Access Statistics for this paper

More papers in Asociación Argentina de Economía Política: Working Papers from Asociación Argentina de Economía Política Contact information at EDIRC.
Bibliographic data for series maintained by Juan Manuel Quintero ().