Can unlisted firms benefit from market information? A data-driven approach

We employ a sample of 10,136 Italian micro-, small-, and mid-sized enterprises (MSMEs) that borrow from 113 cooperative banks to examine whether market pricing of public firms adds additional information to accounting measures in predicting default of private firms. Specifically, we first match the asset prices of listed firms following a data-driven clustering by means of Neural Networks Autoencoder so to evaluate the firm-wise probability of default (PD) of MSMEs. Then, we adopt three statistical techniques, namely linear models, multivariate adaptive regression spline, and random forest to assess the performance of the models and to explain the relevance of each predictor. Our results provide novel evidence that market information represents a crucial indicator in predicting corporate default of unlisted firms. Indeed, we show a significant improvement of the model performance, both on class-specific (F1-score for defaulted class) and overall metrics (AUC) when using market information in credit risk assessment, in addition to accounting information. Moreover, by taking advantage of global and local variable importance technique we prove that the increase in performance is effectively attributable to market information, highlighting its relevant effect in predicting corporate default.