Feature Ranking in Credit-Risk with Qudit-Based Networks

TL;DR

This paper introduces a quantum neural network based on a single qudit for credit risk assessment, achieving high accuracy and interpretability by encoding features and parameters in a unified quantum system, and benchmarking it on real-world data.

Contribution

The paper presents a novel qudit-based quantum neural network that balances predictive performance with interpretability in credit risk modeling.

Findings

QNN outperforms logistic regression in macro-F1 score

QNN matches random forest performance in macro-F1 score

QNN provides interpretable feature importance through learned coefficients

Abstract

In finance, predictive models must balance accuracy and interpretability, particularly in credit risk assessment, where model decisions carry material consequences. We present a quantum neural network (QNN) based on a single qudit, in which both data features and trainable parameters are co-encoded within a unified unitary evolution generated by the full Lie algebra. This design explores the entire Hilbert space while enabling interpretability through the magnitudes of the learned coefficients. We benchmark our model on a real-world, imbalanced credit-risk dataset from Taiwan. The proposed QNN consistently outperforms LR and reaches the results of random forest models in macro-F1 score while preserving a transparent correspondence between learned parameters and input feature importance. To quantify the interpretability of the proposed model, we introduce two complementary metrics: (i) the edit distance between the model's feature ranking and that of LR, and (ii) a feature-poisoning test where selected features are replaced with noise. Results indicate that the proposed quantum model achieves competitive performance while offering a tractable path toward interpretable quantum learning.