Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

3-2026

Abstract

This paper introduces a novel hybrid quantum-classical approach to credit card fraud detection using CVQBoost, a hybrid quantum-classical boosting algorithm executed on the photonic Dirac-3 processor from Quantum Computing Inc. (QCi). By integrating a diverse set of weak classifiers, which includes K-nearest neighbours (KNN), linear discriminant analysis, logistic regression, and XGBoost, within a hybrid quantum-classical ensemble, the proposed method demonstrates significant improvements over the latest published classical benchmarks. Experiments on a Kaggle credit card fraud dataset show that the quantum-enhanced model achieves a mean AUC-PR score of over 0.8, corresponding to an approximately 9% relative improvement over the best published classical baseline. This indicates an improved precision–recall trade-off which can reduce false positives at a fixed recall in operational settings. The study also highlights the trade-off between training runtime and detection performance, with KNN-based ensembles offering superior accuracy at higher computational cost. Results indicate that quantum machine learning pipelines leveraging photonic processors can deliver tangible advantages in rare-event detection tasks, suggesting a promising direction for operational fraud analytics in finance.

Keywords

Quantum Machine Learning (QML), CVQBoost, Fraud Detection, Photonic Quantum Processor, Dirac-3, Quantum Boosting, Credit Card Fraud

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 18th International Conference on Agents and Artificial Intelligence, Marbella, Spain, 2026 March 5-7

First Page

1

Last Page

9

Embargo Period

2-23-2026

Copyright Owner and License

Authors

Download

Share

COinS