CircuitHunt: Automated Quantum Circuit Screening for Superior Credit-Card Fraud Detection

Abstract

Designing effective quantum models for real-world tasks remains a key challenge within Quantum Machine Learning (QML), particularly in applications such as credit card fraud detection, where extreme class imbalance and evolving attack patterns demand both accuracy and adaptability. Most existing approaches rely on either manually designed or randomly initialized circuits, leading to high failure rates and limited scalability. In this work, we introduce CircuitHunt, a fully automated quantum circuit screening framework that streamlines the discovery of high-performing models. CircuitHunt filters circuits from the KetGPT dataset using qubit and parameter constraints, embeds each candidate into a standardized hybrid QNN, and performs rapid training with checkpointing based on macro-F1 scores to discard weak performers early. The top-ranked circuit is then fully trained, achieving 97% test accuracy and a high macro-F1 score on a challenging fraud detection benchmark. By combining budget-aware pruning, empirical evaluation, and end-to-end automation, CircuitHunt reduces architecture search time from days to hours while maintaining performance. It thus provides a scalable and task-driven tool for QML deployment in critical financial applications.