The banks' need of quantitative approaches for credit risk assessment is becoming more and more evident, due to the introduction of the Basel agreements. To this extent, we define an Elman network approach to determine the insolvency of a borrower, and compare its performances with classical neural networks approaches for bankruptcy prediction. Then, we devise an adaptive procedure to select the best network topology, by performing a multi-objective analysis to take into account different compromises between conflicting criteria. We apply our procedure to different real and partly-artificial-case scenarios composed of Italian SMEs by using predictors coming from balance-sheet ratios, credit-history ratios and macro-economic indicators; then, we compare our approach to other ones proposed in the literature and to a standard logistic regression tool used by practitioners; last, given the recent research interest towards the use of qualitative predictors in credit risk assessment, we also apply our approaches on qualitative data. The results show that the Elman networks are effective in assessing credit risk and robust with respect to criteria and data, confirming the applicability of neural networks to bankruptcy prediction. Our contribution adds to the discussion of the ongoing debate about comparing neural networks to standard techniques: in particular, we find Elman Networks to lead to lower classification errors than standard feed-forward networks, whilst results from the comparison to logistic regression vary with respect to the error class considered. As for the data, we remark that the use of macro-economics indicators does not lead to particular improvement in classification accuracy, except when used to improve results coming from the use of qualitative variables only.

The banks’ need of quantitative approaches for credit risk assessment is becoming more and more evident, due to the introduction of the Basel agreements. To this extent, we define an Elman network approach to determine the insolvency of a borrower, and compare its performances with classical neural networks approaches for bankruptcy prediction. Then, we devise an adaptive procedure to select the best network topology, by performing a multi-objective analysis to take into account different compromises between conflicting criteria. We apply our procedure to different real and partly-artificial-case scenarios composed of Italian SMEs by using predictors coming from balancesheet ratios, credit-history ratios and macro-economic indicators; then, we compare our approach to other ones proposed in the literature and to a standard logistic regression tool used by practitioners; last, given the recent research interest towards the use of qualitative predictors in credit risk assessment, we also apply our approaches on qualitative data. The results show that the Elman networks are effective in assessing credit risk and robust with respect to criteria and data, confirming the applicability of neural networks to bankruptcy prediction. Our contribution adds to the discussion of the ongoing debate about comparing neural networks to standard techniques: in particular, we find Elman Networks to lead to lower classification errors than standard feed-forward networks, whilst results from the comparison to logistic regression vary with respect to the error class considered. As for the data, we remark that the use of macro-economics indicators does not lead to particular improvement in classification accuracy, except when used to improve results coming from the use of qualitative variables only.

Design of adaptive Elman networks for credit risk assessment

Marco Corazza
;
Davide De March;Giacomo di Tollo
2020-01-01

Abstract

The banks’ need of quantitative approaches for credit risk assessment is becoming more and more evident, due to the introduction of the Basel agreements. To this extent, we define an Elman network approach to determine the insolvency of a borrower, and compare its performances with classical neural networks approaches for bankruptcy prediction. Then, we devise an adaptive procedure to select the best network topology, by performing a multi-objective analysis to take into account different compromises between conflicting criteria. We apply our procedure to different real and partly-artificial-case scenarios composed of Italian SMEs by using predictors coming from balancesheet ratios, credit-history ratios and macro-economic indicators; then, we compare our approach to other ones proposed in the literature and to a standard logistic regression tool used by practitioners; last, given the recent research interest towards the use of qualitative predictors in credit risk assessment, we also apply our approaches on qualitative data. The results show that the Elman networks are effective in assessing credit risk and robust with respect to criteria and data, confirming the applicability of neural networks to bankruptcy prediction. Our contribution adds to the discussion of the ongoing debate about comparing neural networks to standard techniques: in particular, we find Elman Networks to lead to lower classification errors than standard feed-forward networks, whilst results from the comparison to logistic regression vary with respect to the error class considered. As for the data, we remark that the use of macro-economics indicators does not lead to particular improvement in classification accuracy, except when used to improve results coming from the use of qualitative variables only.
2020
==
File in questo prodotto:
File Dimensione Formato  
2020-Corazza_DeMarch_diTollo-Design_of_adaptive_Elman_networks_for_credit_risk_assessment-QF.pdf

non disponibili

Descrizione: Articolo nella versione dell'editore.
Tipologia: Versione dell'editore
Licenza: Accesso chiuso-personale
Dimensione 1.35 MB
Formato Adobe PDF
1.35 MB Adobe PDF   Visualizza/Apri

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10278/3726339
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact