Machine Learning models for bankruptcy prediction in Italy: do industrial variables count?

Daniela Bragoli, Giovanni Marseguerra, Camilla Ferretti, Piero Ganugi, Mezzogori Davide, Zammori Francesco

Risultato della ricerca: Contributo in libroChapter

Abstract

We aim to provide a predictive model, specifically designed for the Italian economy, which classifies solvent and insolvent firms one year in advance, using AIDA Bureau van Dijk dataset from 2007 to 2015. We apply a full battery of bankruptcy forecasting models, including both traditional and more sophisticated machine learning techniques, and add to the financial ratios used in the literature a set of industrial/regional variables. We find that XGBoost is the best performer and that industrial/regional variables are important. Moreover, belonging to a district, having a high mark up and a greater market share diminish bankruptcy probability.
Lingua originaleEnglish
Titolo della pubblicazione ospiteWorking Paper N. 19/3 DIPARTIMENTO DI MATEMATICA PER LE SCIENZE, ECONOMICHE, FINANZIARIE ED ATTUARIALI
Pagine3-41
Numero di pagine39
Stato di pubblicazionePubblicato - 2019

Keywords

  • firm distress analysis
  • industrial variables
  • logistic regression
  • machine learning

Fingerprint Entra nei temi di ricerca di 'Machine Learning models for bankruptcy prediction in Italy: do industrial variables count?'. Insieme formano una fingerprint unica.

Cita questo