Bankruptcy prediction models in Galician companies. Application of parametric methodologies and artificial intelligence

Abstract

This paper provides empirical evidence on the prediction of non-financial companies’ failure. We develop several models to evaluate failure risk in companies from Galicia. We check the predictive ability of parametric models (multivariate discriminant, logit) compared with auditor’s report. Models are based on relevant financial variables and ratios, in financial logic and a in financial distress situations. We examine a random sample of companies in cross-sectional perspective, checking the predictive capacity at any given time, also verifying is models give reliable signals to anticipate future events of financial distress. Findings suggest that our models are extremely effective when applied in medium and long term, and that they offer higher predictive capabilities than external audit.