Technology has led to the rise of two major fields: Machine Learning and Quantum Information, both shaping modern computer science. This new paradigm holds the promise of intelligent applications across various domains, like fraud detection in finance, high-energy physics, and more. Anomaly detection in finance, in particular, is a significant challenge within financial systems, requiring the development of robust intelligent models. Hyperparameter tuning is critical in optimizing machine learning models to achieve accurate results. This paper explores integration of quantum computing into the hyperparameter tuning process, using Variational Quantum Classifiers and a publicly available financial fraud dataset to compare the performance of quantum-assisted hyperparameter tuning with classical methods, such as Random Forest and XGBoost. The results prove quantum computing’s contribution to improve the model’s performance although some limitations face the quantum technology like noise and qubit count, especially in the context of highly imbalanced datasets. The paper approach provides insights into quantum computing potential in financial fraud detection.