Forecasting sovereign risk in the Euro area via machine learning - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Forecasting Année : 2023

Forecasting sovereign risk in the Euro area via machine learning

Guillaume Belly
Lukas Boeckelmann
  • Fonction : Auteur
Carlos Mateo Caicedo Graciano
Alberto Di Iorio
Vasileios Siakoulis

Résumé

We test the usefulness of machine learning (ML) for the valuation and pricing of sovereign risk in the Euro area along two important dimensions: i) its predictive accuracy compared with traditional econometric methods, and ii) its assessment of the main economic factors underlying market perceptions of sovereign risk.We find that ML techniques can capture the dynamics inherent in the market valuation of country risk far more efficiently than traditional econometric models, both in the cross‐section and in the time series. Moreover, we show that public sentiment about financial news, redenomination fears and the degree of hawkishness/dovishness expressed in the ECB president's speeches are major contributors to sovereign bond spreads. We also confirm that macroeconomic and global financial factors affect sovereign risk assessment and the corresponding formation of sovereign spreads.
Fichier non déposé

Dates et versions

hal-04459577 , version 1 (15-02-2024)

Identifiants

Citer

Guillaume Belly, Lukas Boeckelmann, Carlos Mateo Caicedo Graciano, Alberto Di Iorio, Klodiana Istrefi, et al.. Forecasting sovereign risk in the Euro area via machine learning. Journal of Forecasting, 2023, 42 (3), pp.657-684. ⟨10.1002/for.2938⟩. ⟨hal-04459577⟩
14 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More