Interpretable Selective Learning in Credit Risk

TL;DR

This paper proposes a neural network with a selective option that enhances interpretability in credit risk prediction by identifying when linear models suffice and when more complex models improve accuracy.

Contribution

It introduces a neural network with a selective mechanism to balance interpretability and accuracy in credit risk assessment.

Findings

Logistic regression is sufficient for most datasets with reasonable accuracy.

Selective neural networks improve accuracy on specific data subsets.

The approach maintains interpretability while enhancing predictive performance.

Abstract

The forecasting of the credit default risk has been an important research field for several decades. Traditionally, logistic regression has been widely recognized as a solution due to its accuracy and interpretability. As a recent trend, researchers tend to use more complex and advanced machine learning methods to improve the accuracy of the prediction. Although certain non-linear machine learning methods have better predictive power, they are often considered to lack interpretability by financial regulators. Thus, they have not been widely applied in credit risk assessment. We introduce a neural network with the selective option to increase interpretability by distinguishing whether the datasets can be explained by the linear models or not. We find that, for most of the datasets, logistic regression will be sufficient, with reasonable accuracy; meanwhile, for some specific data portions, a shallow neural network model leads to much better accuracy without significantly sacrificing the interpretability.