Nowcasting world trade with machine learning: a three-step approach

Menzie D. Chinn, Baptiste Meunier and Sebastian Stumpner

No 2836, Working Paper Series from European Central Bank

Abstract: We nowcast world trade using machine learning, distinguishing between tree-based methods (random forest, gradient boosting) and their regression-based counterparts (macroeconomic random forest, linear gradient boosting). While much less used in the literature, the latter are found to outperform not only the tree-based techniques, but also more “traditional” linear and non-linear techniques (OLS, Markov-switching, quantile regression). They do so significantly and consistently across different horizons and real-time datasets. To further improve performances when forecasting with machine learning, we propose a flexible three-step approach composed of (step 1) pre-selection, (step 2) factor extraction and (step 3) machine learning regression. We find that both pre-selection and factor extraction significantly improve the accuracy of machine-learning-based predictions. This three-step approach also outperforms workhorse benchmarks, such as a PCA-OLS model, an elastic net, or a dynamic factor model. Finally, on top of high accuracy, the approach is flexible and can be extended seamlessly beyond world trade. JEL Classification: C53, C55, E37

Keywords: big data; factor model; forecasting; large dataset; pre-selection (search for similar items in EconPapers)
Date: 2023-08
New Economics Papers: this item is included in nep-big, nep-cmp and nep-int
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://www.ecb.europa.eu//pub/pdf/scpwps/ecb.wp2836~6b34f0492c.en.pdf (application/pdf)

Related works:
Working Paper: Nowcasting World Trade with Machine Learning: a Three-Step Approach (2023)
Working Paper: Nowcasting World Trade with Machine Learning: a Three-Step Approach (2023)
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:ecb:ecbwps:20232836

Access Statistics for this paper

More papers in Working Paper Series from European Central Bank 60640 Frankfurt am Main, Germany. Contact information at EDIRC.
Bibliographic data for series maintained by Official Publications ().