Fraud detection in credit card transactions using Quantum-Assisted Restricted Boltzmann Machines
This addresses fraud detection for financial systems, offering a potential improvement but is incremental as it builds on existing quantum-assisted methods.
The paper tackled credit card fraud detection by applying quantum-assisted Restricted Boltzmann Machines to a real dataset of 145 million transactions, achieving superior performance in most figures of merit compared to classical approaches, even on current noisy quantum hardware.
Use cases for emerging quantum computing platforms become economically relevant as the efficiency of processing and availability of quantum computers increase. We assess the performance of Restricted Boltzmann Machines (RBM) assisted by quantum computing, running on real quantum hardware and simulators, using a real dataset containing 145 million transactions provided by Stone, a leading Brazilian fintech, for credit card fraud detection. The results suggest that the quantum-assisted RBM method is able to achieve superior performance in most figures of merit in comparison to classical approaches, even using current noisy quantum annealers. Our study paves the way for implementing quantum-assisted RBMs for general fault detection in financial systems.