Ceris-CNR Working paper 17 /2004
|
Modelli di analisi e previsione
|
Nadia D’Annunzio*, Greta Falavigna**
|
Abstract. During the last three decades various models have been proposed by the literature to predict the risk of bankruptcy and of firm insolvency, which make use of structural and empirical tools, namely rating system, credit scoring, option pricing and three alternative methods (fuzzy logic, efficient frontier and a forward looking model). In the present paper we focus on experting systems of neural networks, by taking into account theoretical as well as empirical literature on the topic. Adding to this literature, a set of alternative indicators is proposed that can be used in addition to traditional financial ratios.
|
Keywords: rischio d’insolvenza, default, neural networks, option pricing, sistemi esperti, algoritmi genetici, logica fuzzy |
JEL: C45, C53, C67, G33 |
* Ceris-Cnr,
Via Avogadro, 8, 10121 Torino
(Italia),
** Università di Bergamo e Ceris-Cnr, I risultati dello studio sono frutto di un lavoro congiunto dei due autori anche se Nadia D’Annunzio ha curato la stesura dei paragrafi 4, 6 e 7, mentre Greta Falavigna ha curato i paragrafi 1, 2, 3 e 5. |