Enhancing variational quantum classifier performance with meta-heuristic feature selection for credit card fraud detection

A transformative hybrid approach is proposed, combining Quantum Machine Learning (QML) with both traditional and meta-heuristic feature selection algorithms to overcome the complexities and limitations of conventional credit card fraud detection methods. In this study, advanced data balancing techniques such as SMOTE-ENN (Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors) and Random Under Sampler (RUS) are employed on the imbalanced European Cardholder Dataset to address class imbalance and enhance model resilience. Core feature selection algorithms-both traditional methods like K-Best and meta-heuristic techniques including Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Atom Search Optimization (ASO)-are systematically evaluated, each paired with the Variational Quantum Classifier (VQC) for classification. Remarkably, the PSO+VQC combination achieves an accuracy rate of 94.54%, underscoring the efficacy of integrating meta-heuristic algorithms with VQC to manage complex, high-dimensional data in fraud detection. These findings highlight QML and meta-heuristic algorithms' potential to surpass conventional methods, delivering superior accuracy and efficiency in critical, data-intensive applications such as financial fraud detection.