Automatic Relevance Determination Bayesian Neural Networks for Credit Card Default Modelling
This work addresses the need for interpretability and uncertainty quantification in credit risk modeling for financial decision-makers, though it is incremental as it applies existing BNN methods to a specific domain.
The paper tackled credit default prediction by developing Bayesian Neural Networks (BNNs) with Automatic Relevance Determination (ARD) for credit card default modeling, showing that ARD BNNs outperform normal BNNs and provide feature importance insights, with Gaussian approximation training performing similarly to Hybrid Monte Carlo on the Taiwan Credit Dataset.
Credit risk modelling is an integral part of the global financial system. While there has been great attention paid to neural network models for credit default prediction, such models often lack the required interpretation mechanisms and measures of the uncertainty around their predictions. This work develops and compares Bayesian Neural Networks(BNNs) for credit card default modelling. This includes a BNNs trained by Gaussian approximation and the first implementation of BNNs trained by Hybrid Monte Carlo(HMC) in credit risk modelling. The results on the Taiwan Credit Dataset show that BNNs with Automatic Relevance Determination(ARD) outperform normal BNNs without ARD. The results also show that BNNs trained by Gaussian approximation display similar predictive performance to those trained by the HMC. The results further show that BNN with ARD can be used to draw inferences about the relative importance of different features thus critically aiding decision makers in explaining model output to consumers. The robustness of this result is reinforced by high levels of congruence between the features identified as important using the two different approaches for training BNNs.