A0404
Title: Understanding corporate default: The role of accounting and market information with a cluster-based matching procedure
Authors: Alessandro Bitetto - University of Pavia (Italy) [presenting]
Michele Modina - University of Molise (Italy)
Stefano Filomeni - University of Essex - Essex Business School (United Kingdom)
Abstract: Recent evidence highlights the importance of hybrid credit scoring models in evaluating borrowers' creditworthiness. However, the current hybrid models neglect to consider the role of public-peer market information in addition to accounting information on default prediction. Novel evidence is provided on the impact of market information in predicting corporate defaults for unlisted firms. A sample of 10,136 Italian micro-, small-, and mid-sized enterprises (MSMEs) is employed that borrow from 113 cooperative banks from 2012-2014 to examine whether market pricing of public firms adds additional information to accounting measures in predicting the default of private firms. Specifically, the probability of default (PD) of MSMEs is estimated using equity price of size-and industry-matched public firms, and then advanced statistical techniques based on the parametric algorithm (multivariate adaptive regression spline) and non-parametric machine learning model (random forests) are adopted. Moreover, by using Shapley values, the relevance of market information in predicting corporate credit risk is assessed. Firstly, the predictive power of Merton's PD on default prediction is shown for unlisted firms. Secondly, the increased predictive power of credit risk models that consider both the Merton's PD and accounting information to assess corporate credit risk is shown.
