EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

Generalisation Bounds of Zero-Shot Economic Forecasting Using Time Series Foundation Models

Jittarin Jetwiriyanon, Teo Susnjak, Surangika Ranathunga

Machine Learning and Knowledge Extraction · 2025-11-03 · 7 (4) · 135

DOI: 10.3390/make7040135 ↗

At a glance

Journal article in Machine Learning and Knowledge Extraction, published online on 2025-11-03. Written by Jittarin Jetwiriyanon and 2 co-authors. Cited 8 times so far (Crossref); 87 references. The full text is freely available (open access, CC BY 4.0).

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

This study investigates the transfer learning capabilities of Time-Series Foundation Models (TSFMs) under the zero-shot setup, to forecast macroeconomic indicators. New TSFMs are continually emerging, offering significant potential to provide ready-trained and accurate forecasting models that generalise across a wide spectrum of domains. However, the transferability of their learning to many domains, especially economics, is not well understood. To that end, we study TSFM’s performance profile for economic forecasting, bypassing the need for training bespoke econometric models using extensive training datasets. Our experiments were conducted on a univariate case study dataset, in which we rigorously back-tested three state-of-the-art TSFMs (Chronos, TimeGPT, and Moirai) under data-scarce conditions and structural breaks. Our results demonstrate that appropriately engineered TSFMs can internalise rich economic dynamics, accommodate regime shifts, and deliver well-behaved uncertainty estimates out of the box, while matching and exceeding state-of-the-art multivariate models currently used in this domain. Our findings suggest that, without any fine-tuning and additional multivariate inputs, TSFMs can match or outperform classical models under both stable and volatile economic conditions. However, like all models, they are vulnerable to performance degradation during periods of rapid shocks, though they recover the forecasting accuracy faster than classical models. The findings offer guidance to practitioners on when zero-shot deployments are viable for macroeconomic monitoring and strategic planning.

Cite

APA

Jetwiriyanon, J., Susnjak, T., & Ranathunga, S. (2025). Generalisation Bounds of Zero-Shot Economic Forecasting Using Time Series Foundation Models. Machine Learning and Knowledge Extraction, 7(4), 135. https://doi.org/10.3390/make7040135

Vancouver

Jetwiriyanon J, Susnjak T, Ranathunga S. Generalisation Bounds of Zero-Shot Economic Forecasting Using Time Series Foundation Models. Machine Learning and Knowledge Extraction. 2025;7(4):135. doi:10.3390/make7040135

BibTeX
@article{Jetwiriyanon2025,
  author = {Jetwiriyanon, Jittarin and Susnjak, Teo and Ranathunga, Surangika},
  title = {Generalisation Bounds of Zero-Shot Economic Forecasting Using Time Series Foundation Models},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2025},
  volume = {7},
  number = {4},
  pages = {135},
  doi = {10.3390/make7040135}
}
Start for free →