I modelli di previsione delle insolvenze: una prospettiva territoriale

Purpose: To test whether the qualitative variables regarding the territory and the firm-territory relationship can improve the accuracy of small business default prediction models. Methodology: we applied a logistic regression to a sample of 141 small Italian enterprises located in the Marche region and we built two different default prediction models: one using only financial ratios and one using jointly financial ratios and territorial variables. Findings: Including variables regarding the relationships between firms and their territory the accuracy rates of default prediction models is significantly improved. Research limits: The qualitative variables data collected are affected by subjective judgments of respondents of the firms studied. In addition, no other qualitative variables (such as those regarding competitive strategies, the managerial skills and the knowledge management) were included. Practical implications: The study suggests the possibility for the management to adopt a model of diagnosis of the health of businesses and the opportunities for financial institutions, to integrate the qualitative variables related to the territory and firm-territory relationship in their credit rating models. In a perspective of strategic control, default prediction models can serve as instruments of ex ante evaluation of business performance and of the first symptom of difficulty. Originality of the study: In literature there are a very few previous studies on the contribution of the aspects relating to the territory for the default prediction of enterprises.