Emiliano Mastrolia

Modelli di stima della probabilità di default: Il caso di una banca locale

  • Abstract

Informations and abstract

Keywords: default, credit scoring, discriminant analysis, logistic regression.

Based on a sample of 496 firms from the loans portfolio of a local bank and using financial variables we estimate a linear discriminant function for predicting firm default and we used a logistic model to estimate the probability of default. Results highlight that both the models are able to correctly classify over the 95% of sampled firms. However, logistic regression has a better performance in reducing type I error. Therefore, logistic regression represents a useful tool for estimating the probability of default of firms and for improving credit management strategies.

Trova nel catalogo di Worldcat

Article first page

Article first page