Forecasting Sovereign Risk in the Euro Area via Machine Learning

46 Pages Posted: 30 Nov 2021 Last revised: 10 Jul 2024

See all articles by Guillaume Belly

Guillaume Belly

Banque de France

Boeckelmann Lukas

Banque de France

Carlos Mateo Caicedo Graciano

Banque de France

Alberto Di Iorio

Bank of Italy

Klodiana Istrefi

Banque de France; Centre for Economic Policy Research (CEPR)

Vasileios Siakoulis

Bank of Greece

Arthur Stalla-Bourdillon

Banque de France

Date Written: November 30, 2021

Abstract

We test the usefulness of Machine Learning (ML) for sovereign risk assessment and pricing in the euro area along two important dimensions: i) their predictive accuracy compared to traditional econometrics methods and, ii) their assessment on what are the most important economic factors behind market perception of sovereign risk. We find that ML techniques can capture the dynamics inherent in market assessment of sovereign risk in a far more efficient way than traditional econometric models, both in a cross section and time series setting. Moreover, we show that public sentiment about financial news, redenomination fears and the degree of hawkishness/dovishness expressed in the ECB president speeches, rank high as contributors for sovereign spreads. We also confirm that macroeconomic and global financial factors affect sovereign risk assessment and the respective formation of sovereign spreads.

Keywords: Sovereign Risk, Machine Learning, forecasting, euro area, Google Trends, Text Mining, XGBOOST, Support Vector Machines, Neural Networks, Random Forests.

JEL Classification: G01, G21, C53

Suggested Citation

Belly, Guillaume and Lukas, Boeckelmann and Caicedo Graciano, Carlos Mateo and Di Iorio, Alberto and Istrefi, Klodiana and Siakoulis, Vasileios and Stalla-Bourdillon, Arthur, Forecasting Sovereign Risk in the Euro Area via Machine Learning (November 30, 2021). Available at SSRN: https://ssrn.com/abstract=3974515 or http://dx.doi.org/10.2139/ssrn.3974515

Guillaume Belly

Banque de France ( email )

Paris
France

Boeckelmann Lukas

Banque de France ( email )

Paris
France

Carlos Mateo Caicedo Graciano

Banque de France ( email )

31 rue Croix-des-Petits-Champs
Paris, 75001
France
+33142929650 (Phone)

HOME PAGE: http://https://www.banque-france.fr/

Alberto Di Iorio

Bank of Italy ( email )

Via Nazionale 91
Rome, 00184
Italy

Klodiana Istrefi

Banque de France ( email )

Paris
France

Centre for Economic Policy Research (CEPR) ( email )

London
United Kingdom

Vasileios Siakoulis (Contact Author)

Bank of Greece ( email )

21 E. Venizelos Avenue
GR 102 50 Athens
Greece

Arthur Stalla-Bourdillon

Banque de France ( email )

Paris
France

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
197
Abstract Views
1,002
Rank
289,315
PlumX Metrics