Credit rating is the evaluation of the likelihood of an obligor to default on a loan. Each obligor in the bank’s credit portfolio isassigned to a certain rating class, or PD (probability of default) bucket; all obligors in a PD bucket then receive the same “pooled”PD, based on which a capital charge against credit risk must be computed. The only analytical approach to this problem is basedon k-means and has some limitations in practice. An error minimization approach to credit rating using differential evolution (DE)is introduced. The performances of DE and other common search heuristics are compared using credit rating data of a major Italianbank. Empirical results show that DE is clearly superior compared to a genetic algorithm (GA), particle swarm optimization (PSO),random search (RS) and two naïve partitioning approaches. Moreover, the proposed approach obtained better results than k-meansin much less runtime for a simplified instance of the problem where within-groups variances can be used for clustering.

Using Differential Evolution to improve the accuracy of bank rating systems / Krink, T; Paterlini, Sandra; Resti, A.. - In: COMPUTATIONAL STATISTICS & DATA ANALYSIS. - ISSN 0167-9473. - STAMPA. - 52:1(2007), pp. 68-87. [10.1016/j.csda.2007.02.011]

Using Differential Evolution to improve the accuracy of bank rating systems

PATERLINI, Sandra;
2007

Abstract

Credit rating is the evaluation of the likelihood of an obligor to default on a loan. Each obligor in the bank’s credit portfolio isassigned to a certain rating class, or PD (probability of default) bucket; all obligors in a PD bucket then receive the same “pooled”PD, based on which a capital charge against credit risk must be computed. The only analytical approach to this problem is basedon k-means and has some limitations in practice. An error minimization approach to credit rating using differential evolution (DE)is introduced. The performances of DE and other common search heuristics are compared using credit rating data of a major Italianbank. Empirical results show that DE is clearly superior compared to a genetic algorithm (GA), particle swarm optimization (PSO),random search (RS) and two naïve partitioning approaches. Moreover, the proposed approach obtained better results than k-meansin much less runtime for a simplified instance of the problem where within-groups variances can be used for clustering.
2007
52
1
68
87
Using Differential Evolution to improve the accuracy of bank rating systems / Krink, T; Paterlini, Sandra; Resti, A.. - In: COMPUTATIONAL STATISTICS & DATA ANALYSIS. - ISSN 0167-9473. - STAMPA. - 52:1(2007), pp. 68-87. [10.1016/j.csda.2007.02.011]
Krink, T; Paterlini, Sandra; Resti, A.
File in questo prodotto:
File Dimensione Formato  
7_krink_paterlini_compstat_final copy.pdf

Accesso riservato

Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 337.3 kB
Formato Adobe PDF
337.3 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/585428
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 29
  • ???jsp.display-item.citation.isi??? 25
social impact