Using the European Commission country recommendations to predict sovereign ratings: A topic modeling approach

Abstract This paper examines the role of textual and unstructured data in the credit risk assessment of sovereigns. Specifically, in this paper, a novel approach to understand and predict sovereign ratings is proposed. For that purpose, information embedded in the annual country reports issued by the European Commission is used. The model employs a neural-network-based document embedding known as document to vector (Doc2Vec) to convert each country report into a numerical vector, which is then used as features into a logistic regression. The model is trained using information from 2011 to 2019 and it correctly predicts the 70.27% of country ratings in the test sample, improving slightly the results obtained using only macroeconomic variables.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Manfred Gärtner,et al.  PIGS or Lambs? The European Sovereign Debt Crisis and the Role of Rating Agencies , 2011 .

[3]  M. Wickens,et al.  Sovereign Credit Ratings in the European Union: A Model-Based Fiscal Analysis , 2013 .

[4]  Juliana Yim,et al.  Comparison of country risk models: hybrid neural networks, logit models, discriminant analysis and cluster techniques , 2005, Expert Syst. Appl..

[5]  P. Rowland,et al.  Determinants of Spread and Creditworthiness for Emerging Market Sovereign Debt:A Panel Data Study , 2004 .

[6]  N. Apergis.  Newswire messages and sovereign credit ratings: Evidence from European countries under austerity reform programmes , 2015 .

[7]  Emawtee Bissoondoyal-Bheenick,et al.  An analysis of the determinants of sovereign ratings , 2005 .

[8]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[9]  Marco Pagano,et al.  Credit Ratings Failures and Policy Options , 2009 .

[10]  Johan A. K. Suykens,et al.  A process model to develop an internal rating system: Sovereign credit ratings , 2006, Decis. Support Syst..

[11]  Xiaoming Li,et al.  A comparison of the economic performance of different micro-states, and between micro-states and larger countries , 1998 .

[12]  R. Brooks,et al.  Determinants of Sovereign Ratings: A Comparison of Case-Based Reasoning and Ordered Probit Approaches , 2006 .

[13]  Lourdes Treviño,et al.  Local vs Foreign Currency Ratings: What Determines Sovereign Transfer Risk? , 2001 .

[14]  Antonio Afonso,et al.  Short‐ and long‐run determinants of sovereign debt credit ratings , 2011 .

[15]  Richard Cantor,et al.  Determinants and Impact of Sovereign Credit Ratings , 1996 .

[16]  Sheng-Syan Chen,et al.  The relation between sovereign credit rating revisions and economic growth , 2016 .

[17]  Nada Mora,et al.  Sovereign credit ratings: Guilty beyond reasonable doubt? , 2006 .

[18]  Erik F. Nielsen,et al.  The Damaging Bias of Sovereign Ratings , 2015 .

[19]  Carmen M. Reinhart,et al.  Ratings, Rating Agencies and the Global Financial System , 2002 .

[20]  Stephen Thomas,et al.  Modelling sovereign credit ratings: Neural networks versus ordered probit , 2006, Expert Syst. Appl..

[21]  Paolo Manasse,et al.  'Rules of Thumb' for Sovereign Debt Crises , 2005, SSRN Electronic Journal.

[22]  J. Bessis,et al.  Risk Management in Banking , 1998 .

[23]  S. Lee.  Are the credit ratings assigned by bankers based on the willingness of LDC borrowers to repay , 1993 .

[24]  Robert W. Faff,et al.  Variations in sovereign credit quality assessments across rating agencies , 2010 .

[25]  Patricio Valenzuela,et al.  Financial openness, domestic financial development and credit ratings , 2016 .

[26]  Antonello D’Agostino,et al.  Euro Area Sovereign Ratings: An Analysis of Fundamental Criteria and Subjective Judgement , 2016 .

[27]  W. Perraudin,et al.  The Estimation of Transition Matrices for Sovereign Credit Ratings , 2002 .

[28]  Brieuc Monfort,et al.  Using Credit Ratings for Capital Requirements on Lending to Emerging Market Economies: Possible Impact of a New Basel Accord , 2000, SSRN Electronic Journal.

[29]  Kurt Hornik,et al.  Text Mining Infrastructure in R , 2008 .

[30]  J. Gnabo,et al.  The Importance of Conflicts of Interest in Attributing Sovereign Credit Ratings , 2015 .

[31]  Peter L. Hammer,et al.  A NON-RECURSIVE REGRESSION MODEL FOR COUNTRY RISK RATING , 2003 .

[32]  Antonio Afonso,et al.  Understanding the determinants of sovereign debt ratings: Evidence for the two leading agencies , 2002 .