Quantum Machine Learning Model for Credit Card Fraud Assessment with Ensemble Learners

Abstract

Credit card frauds are placing a great challenge over financial systems. The traditional rule based systems often fail to handle sophisticated fraudulent techniques. In this model we are applying Feed forward Neural Networks with a multi-layer perceptron to identify imbalanced transactional data with advanced preprocessing, scaling and classification. This model can interpret complex transaction patterns effectively to minimize misclassification. On the other hand Quantum techniques improve the ability to data ETL process over IoT devices in banking systems. The Quantum Machine Learning adoption improves the processing capacity with great minimization of computational devices size. The Quantum Computing delivers high precession and accuracy with fast processing of digital information.