Understanding the correlation between different customers’ loss of creditworthiness is crucial to credit risk analysis. This paper describes a novel method, based on a weighted network model, in which a set of firms, customers of the same bank, represent the nodes while their links and weights derive from the total transaction amounts. We explore the contagion mechanism deriving from the transmission of the difficulties of one customer to other clients of the same bank so highlighting areas where contagion risk is higher. We use a real proprietary data set provided by a bank to illustrate the proposed pproach
Dangerous liasons and hot customers for banks
A. G. Quaranta
2022-01-01
Abstract
Understanding the correlation between different customers’ loss of creditworthiness is crucial to credit risk analysis. This paper describes a novel method, based on a weighted network model, in which a set of firms, customers of the same bank, represent the nodes while their links and weights derive from the total transaction amounts. We explore the contagion mechanism deriving from the transmission of the difficulties of one customer to other clients of the same bank so highlighting areas where contagion risk is higher. We use a real proprietary data set provided by a bank to illustrate the proposed pproachFile in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
s11156-022-01039-x_PUBBLICATO.pdf
solo utenti autorizzati
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
DRM non definito
Dimensione
1.5 MB
Formato
Adobe PDF
|
1.5 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.