Random forest versus logit models: Which offers better early warning of fiscal stress?

Arbeitspapier

This study seeks to answer whether it is possible to design an early warning system framework that can signal the risk of fiscal stress in the near future, and what shape such a system should take. To do so, multiple models based on econometric logit and the random forest models are designed and compared. Using a dataset of 20 annual frequency variables pertaining to 43 advanced and emerging countries during 1992-2018, the results confirm the possibility of obtaining an effective model, which correctly predicts 70-80% of fiscal stress events and tranquil periods. The random forest-based early warning model outperforms logit models. While the random forest model is commonly understood to provide lower interpretability than logit models do, this study employs tools that can be used to provide useful information for understanding what is behind the black-box. These tools can provide information on the most important explanatory variables and on the shape of the relationship between these variables and the outcome classification. Thus, the study contributes to the discussion on the usefulness of machine learning methods in economics.

Angaben zum Objekt

• ISBN: 978-92-899-4051-1
• Sprache: Englisch

Verweise und Beziehungen

• Erschienen in: Series: ECB Working Paper ; No. 2408

Klassifikation und Themen

• Klassifikation: Wirtschaft ; Econometric and Statistical Methods: Special Topics: General ; Forecasting Models; Simulation Methods ; National Debt; Debt Management; Sovereign Debt ; Financial Crises
• Thema: early warning system ; interpretability of machine learning ; predictive performance

Beteiligte, Orts- und Zeitangaben

• Ereignis: Geistige Schöpfung
• (wer): Jarmulska, Barbara
• Ereignis: Veröffentlichung
• (wer): European Central Bank (ECB)
• (wo): Frankfurt a. M.
• (wann): 2020

Weitere Informationen

• DOI: doi:10.2866/214327
• Handle: http://hdl.handle.net/10419/229022
• Letzte Aktualisierung: 10.03.2025, 11:43 MEZ