Enhancing Accuracy of Financial Fraud Detection through Comparative Analysis of Classical and Quantum SVM Approaches
M. Chaitanya Kumari, G.Murali
Quantum Computing is not a new subject, it is just the application of the concepts of Quantum Mechanics (like Entanglement, Superposition and inference) for Data Analysis and computation using these principles, where the classical approaches of computation be unable to. Today, financial fraud are becoming more and more sophisticated and difficult to be discovered by traditional methods. This paper intends to analyze the efficiency of QSVMs and classical Machine Learning in the context of fraud detection. The work aims at verifying if quantum-enhanced kernel methods can provide better classification results for the imbalanced financial data with non-linear patterns between classes, comparing to classical models. The contribution also analyzes practical limitations and reality constraints of working with QSVM, on the financial anomaly detection use case, as well as its feasibility on SOTA real quantum hardware.
IEEE International Conference on Emerging Computing and Intelligent Technologies (ICoECIT)•Jan 28, 2026•0 citations