IQNN-CS: Interpretable Quantum Neural Network for Credit Scoring

2025-10-16

AI Summary

Quantum machine learning (QML) faces adoption barriers in financial credit scoring due to its “black-box” nature, which undermines interpretability and regulatory compliance. Method: This paper proposes the first explainable quantum neural network framework tailored for multi-class credit risk classification. It integrates variational quantum neural networks with structured-data-adapted posterior explanation techniques and introduces the inter-class attribution alignment (ICAA) metric—a novel quantitative measure of feature attribution discrepancies across risk classes. Contribution/Results: Experiments on real-world credit datasets demonstrate that the framework achieves stable training dynamics, superior classification accuracy (significantly outperforming classical baselines), and enhanced decision transparency. It establishes a new paradigm for trustworthy QML deployment in high-stakes financial domains, backed by empirical validation.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Interpretability, Explainability, and Transparency
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Credit scoring is a high-stakes task in financial services, where model decisions directly impact individuals' access to credit and are subject to strict regulatory scrutiny. While Quantum Machine Learning (QML) offers new computational capabilities, its black-box nature poses challenges for adoption in domains that demand transparency and trust. In this work, we present IQNN-CS, an interpretable quantum neural network framework designed for multiclass credit risk classification. The architecture combines a variational QNN with a suite of post-hoc explanation techniques tailored for structured data. To address the lack of structured interpretability in QML, we introduce Inter-Class Attribution Alignment (ICAA), a novel metric that quantifies attribution divergence across predicted classes, revealing how the model distinguishes between credit risk categories. Evaluated on two real-world credit datasets, IQNN-CS demonstrates stable training dynamics, competitive predictive performance, and enhanced interpretability. Our results highlight a practical path toward transparent and accountable QML models for financial decision-making.

Problem

• Develops interpretable quantum neural network for credit scoring
• Addresses black-box nature of quantum machine learning models
• Introduces metric to quantify attribution divergence across risk categories

Innovation

• Interpretable quantum neural network for credit scoring
• Combines variational QNN with post-hoc explanation techniques
• Introduces Inter-Class Attribution Alignment metric for interpretability