Do global forecasting models require frequent retraining?

Marco Zanotti

No 551, Working Papers from University of Milano-Bicocca, Department of Economics

Abstract: In an era of increasing computational capabilities and growing environmental consciousness, organizations face a critical challenge in balancing the accuracy of their forecasting models with computational efficiency and sustainability. Global forecasting models, which leverage data across multiple time series to improve prediction accuracy, lowering the computational time, have gained significant attention over the years. However, the common practice of retraining these models with new observations raises important questions about the costs of producing forecasts. Using ten different machine learning and deep learning models, we analyzed various retraining scenarios, ranging from continuous updates to no retraining at all, across two large retail datasets. We showed that less frequent retraining strategies can maintain the forecast accuracy while reducing the computational costs, providing a more sustainable approach to large-scale forecasting. We also found that machine learning models are a marginally better choice to reduce the costs of forecasting when coupled with less frequent model retraining strategies as the frequency of the data increases. Our findings challenge the conventional belief that frequent retraining is essential for maintaining forecasting accuracy. Instead, periodic retraining offers a good balance between predictive performance and efficiency, both in the case of point and probabilistic forecasting. These insights provide actionable guidelines for organizations seeking to optimize forecasting pipelines while reducing costs and energy consumption.

Keywords: Time series; Demand forecasting; Forecasting competitions; Cross-learning; Global models; Machine learning; Deep learning; Green AI; Conformal predictions. (search for similar items in EconPapers)
JEL-codes: C52 C53 C55 (search for similar items in EconPapers)
Pages: 39
Date: 2025-04
New Economics Papers: this item is included in nep-big, nep-cmp, nep-env and nep-for
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://repec.dems.unimib.it/repec/pdf/mibwpaper551.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:mib:wpaper:551

Access Statistics for this paper

More papers in Working Papers from University of Milano-Bicocca, Department of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Matteo Pelagatti ().