Look Who's Talking: Interpretable Machine Learning for Assessing Italian SMEs Credit Default

TL;DR

This paper develops an interpretable machine learning framework for predicting credit default among Italian SMEs, combining high predictive accuracy with explainability using model-agnostic tools like SHAP and ALE.

Contribution

It introduces a model-agnostic interpretability approach to credit default prediction, enhancing transparency without sacrificing performance for Italian SMEs.

Findings

eXtreme Gradient Boosting outperforms other models in classification accuracy.

The interpretability tools effectively identify key predictors influencing default risk.

The approach balances high performance with model transparency in financial risk assessment.

Abstract

Academic research and the financial industry have recently paid great attention to Machine Learning algorithms due to their power to solve complex learning tasks. In the field of firms' default prediction, however, the lack of interpretability has prevented the extensive adoption of the black-box type of models. To overcome this drawback and maintain the high performances of black-boxes, this paper relies on a model-agnostic approach. Accumulated Local Effects and Shapley values are used to shape the predictors' impact on the likelihood of default and rank them according to their contribution to the model outcome. Prediction is achieved by two Machine Learning algorithms (eXtreme Gradient Boosting and FeedForward Neural Network) compared with three standard discriminant models. Results show that our analysis of the Italian Small and Medium Enterprises manufacturing industry benefits from the overall highest classification power by the eXtreme Gradient Boosting algorithm without giving up a rich interpretation framework.