Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2208.07963 · IEEE Transactions on Quantum Engineering

Mixed Quantum–Classical Method for Fraud Detection With Quantum Feature Selection

Michele Grossi, Noelle Ibrahim, Voica Ana Maria Radescu, Robert Loredo, Kirsten Voigt, Constantin von Altrock, Andreas Rudnik

Published Jan 1, 2022• 111 citations
arXivHTMLPDF

Abstract

This paper presents a first end-to-end application of a Quantum Support Vector Machine (QSVM) algorithm for a classification problem in the financial payment industry using the IBM Safer Payments and IBM Quantum Computers via the Qiskit software stack. Based on real card payment data, a thorough comparison is performed to assess the complementary impact brought in by the current state-of-the-art Quantum Machine Learning algorithms with respect to the Classical Approach. A new method to search for best features is explored using the Quantum Support Vector Machine's feature map characteristics. The results are compared using fraud specific key performance indicators: Accuracy, Recall, and False Positive Rate, extracted from analyses based on human expertise (rule decisions), classical machine learning algorithms (Random Forest, XGBoost) and quantum-based machine learning algorithms using QSVM. In addition, a hybrid classical-quantum approach is explored by using an ensemble model that combines classical and quantum algorithms to better improve the fraud prevention decision. We found, as expected, that the results highly depend on feature selections and algorithms that are used to select them. The QSVM provides a complementary exploration of the feature space which led to an improved accuracy of the mixed quantum-classical method for fraud detection, on a drastically reduced data set to fit current state of Quantum Hardware.

DOI
10.1109/tqe.2022.3213474

Related papers

Quantum Machine Learning Technique for Insurance Claim Fraud Detection with Quantum Feature Selection

Subodh Nath Pushpak

This paper demonstrates a novel use of quantum machine learning (QML) algorithms for detecting fraudulent activities in the home insurance sector. Utilizing actual data and IBM Quantum processors through the Qiskit software stack, the study introduces an innovative method for selecting quantum features that are specifically designed to accommodate the limitations of Near Intermediate Scale Quantum (NISQ) technology by using the Quantum Support Vector Machine (QSVM) in conjunction with traditional machine learning techniques. A comprehensive comparison was conducted to evaluate their effectiveness in detecting fraud. The indicators such as accuracy, recall, and false positive rate are carefully analyzed. Despite the constraints of current quantum technology, QSVM shows excellent accuracy, especially on limited datasets, indicating its potential to enhance insurance fraud detection. The research emphasizes the crucial feature selection in optimizing QML algorithms for fraud detection tasks. It investigates the capacities of hybrid quantum/classical machine learning ensembles. Future research directions include expanding this study to actual hardware implementations to verify its practical feasibility. The work enhances financial security in the insurance business by using quantum computing technology in fraud detection approaches. It establishes the feasibility and efficacy of using quantum resources to solve difficult real-world issues, setting a foundation for or the broader application of QML in fraud detection and other fields.

Journal of Information Systems Engineering & Management•Jan 31, 2025•2 citations

FD4QC: Application of Classical and Quantum-Hybrid Machine Learning for Financial Fraud Detection A Technical Report

Matteo Cardaioli, Luca Marangoni, Martini, Giada +5 more

The increasing complexity and volume of financial transactions pose significant challenges to traditional fraud detection systems. This technical report investigates and compares the efficacy of classical, quantum, and quantum-hybrid machine learning models for the binary classification of fraudulent financial activities. As of our methodology, first, we develop a comprehensive behavioural feature engineering framework to transform raw transactional data into a rich, descriptive feature set. Second, we implement and evaluate a range of models on the IBM Anti-Money Laundering (AML) dataset. The classical baseline models include Logistic Regression, Decision Tree, Random Forest, and XGBoost. These are compared against three hybrid classic quantum algorithms architectures: a Quantum Support Vector Machine (QSVM), a Variational Quantum Classifier (VQC), and a Hybrid Quantum Neural Network (HQNN). Furthermore, we propose Fraud Detection for Quantum Computing (FD4QC), a practical, API-driven system architecture designed for real-world deployment, featuring a classical-first, quantum-enhanced philosophy with robust fallback mechanisms. Our results demonstrate that classical tree-based models, particularly \textit{Random Forest}, significantly outperform the quantum counterparts in the current setup, achieving high accuracy (\(97.34\%\)) and F-measure (\(86.95\%\)). Among the quantum models, \textbf{QSVM} shows the most promise, delivering high precision (\(77.15\%\)) and a low false-positive rate (\(1.36\%\)), albeit with lower recall and significant computational overhead. This report provides a benchmark for a real-world financial application, highlights the current limitations of quantum machine learning in this domain, and outlines promising directions for future research.

arXiv:2507.19402•Jul 25, 2025•0 citations

Enhancing Hybrid Quantum-Classical Fraud Detection Using Imbalance-Aware Learning Techniques

P. Shreya Prabhalitha, Hazarath Murali Krishna Prasad, Munaga H.M

The increasing dependence on digital and card-based payment systems has heightened the risk of financial fraud. This situation creates an urgent need for models that can identify rare fraudulent events in uneven transaction data. Traditional machine learning models often sacrifice recall for precision when the minority class is very small. Quantum classifiers are theoretically appealing for capturing complex feature relationships, but current hardware limitations on qubit count and circuit depth restrict their effectiveness. This work introduces a hybrid quantum-classical framework for credit card fraud detection. It combines an Extreme Gradient Boosting (XGBoost) classifier with a Quantum Support Vector Machine (QSVM) that uses a ZZ feature map and a fidelity-based quantum kernel. To handle class imbalance, we apply the Synthetic Minority Oversampling Technique (SMOTE) and adjust decision thresholds. The quantum element is trained on a reduced, class-balanced data subset, ensuring it stays within the feasible limits of the simulator. We merge predictions from the classical and quantum models using a weighted probability fusion approach, optimizing the final threshold to maximize the F1-score. Using the Kaggle Credit Card Fraud Detection dataset, the hybrid model achieves a precision of 0.9783, recall of 0.9000, F1-score of 0.9375, and ROC-AUC of 0.9805. It surpasses the standalone XGBoost baseline, XGBoost with SMOTE, and the standalone QSVM regarding F1 and ROC-AUC metrics. These results show that blending classical gradient boosting with quantum kernel-based classification, along with imbalance-aware techniques, can significantly enhance fraud detection quality despite current quantum hardware limitations. This offers a practical path for future work in quantum-assisted financial security.

•Jan 1, 2026•0 citations

Hybrid Quantum-Classical Models and Optimization Techniques for Financial Fraud Detection

K. Deepa, Raunak Singh, Kondapuram Tharun

Every day machine learning in financial systems is increasing with financial institutions taking every steps in their power to detect and block counterfeit transactions. Today, modern electronic payment instruments and financial facilities are becoming more and more susceptible to new methods of fraud which are unobtrusively reproducing the activities of legitimate interests to the detriment of the economy which is losing incalculable sums of money. In order to overcome this the combination technique of quantum and classical methods of calculating the data is a great way to enhance the reliability and accuracy of the fraud detection. It is applied by means of Quantum Support Vector Machine, Variational Quantum Classifier, the classical algorithms of Support Vector Machine and K-Nearest Neighbor with an ensemble based on Quadratic Unconstrained Binary Optimization. These algorithms are used together to scan a stream of transactions in real time and classify what is legitimate behaviour and what is unfavourable behaviour. The work provides evidence to prove that hybrid quantum-classical techniques can improve on the performance of classical systems using improved recall, less false negatives and the speed of detection of new types of frauds. It is shown that the integration of quantum intelligence based upon classical methods of analysis is a powerful and fruitful means to enhance levels of secure financial practice and help combat large scale financial frauds in modern digital environments.

International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS)•Dec 15, 2025•0 citations

CREDIT CARD FRAUD DETECTION USING QUANTUM MACHINE LEARNING: A HYBRID CLASSICAL-QUANTUM APPROACH

Akanksha Reddy, A. Sripriya, J. Nihanth Reddy +3 more

With the rapid growth of digital financial transactions, credit card fraud detection has become a critical challenge in the banking and finance sector. Traditional rule-based systems and classical machine learning (ML) models often struggle to detect complex and evolving fraud patterns, especially in highly imbalanced datasets. This paper proposes a novel hybrid approach to credit card fraud detection using Quantum Machine Learning (QML) techniques combined with classical methods. The system applies Principal Component Analysis (PCA) for dimensionality reduction and Synthetic Minority Oversampling Technique (SMOTE) to handle class imbalance. A classical Random Forest model is implemented as a baseline, while a QML model based on Variational Quantum Circuits (VQC) is developed using PennyLane. A hybrid decision engine combining predictions of both models is designed for improved performance. Experimental results demonstrate that the hybrid model achieves 96.9% accuracy, outperforming individual models by achieving better detection rates and reducing false predictions. The system is deployed via an interactive Streamlit-based dashboard. This work highlights the potential of Quantum Machine Learning in enhancing fraud detection systems in financial security applications.

Research Digest on Engineering Management and Social Innovations•Apr 24, 2026•0 citations

Quantum Support Vector Machine for Fraud Detection

Liang Ren, Xuesong Zhang

Quantum algorithms have demonstrated extraordinary potential in numerous fields. The demand for fraud detection in credit cards is growing increasingly, which calls for more efficient algorithms. This work adopts the detection method of Quantum Support Vector Machine (QSVM) to improve the accuracy of credit card fraud detection. Meanwhile, Quantum-Synthetic Minority Oversampling Technique (Quantum-SMOTE) is utilized to address the issue of imbalanced credit card datasets. The QSVM model maps classical data to a high-dimensional Hilbert space through quantum feature mapping, thereby enhancing the separability of features. Then, quantum kernel computation is performed to calculate the inner products between features for model training. The research results show that the QSVM achieves the best overall performance, which indicates that QSVM has significant potential in handling credit card fraud detection.

International Conference on Computing, Communication, Perception and Quantum Technology (CCPQT)•Oct 24, 2025•1 citation
This paper presents a first end-to-end application of a Quantum Support Vector Machine (QSVM) algorithm for a classification problem in the financial payment industry using the IBM Safer Payments and IBM Quantum Computers via the Qiskit software stack. Based on real card payment data, a thorough comparison is performed to assess the complementary impact brought in by the current state-of-the-art Quantum Machine Learning algorithms with respect to the Classical Approach. A new method to search for best features is explored using the Quantum Support Vector Machine's feature map characteristics. The results are compared using fraud specific key performance indicators: Accuracy, Recall, and False Positive Rate, extracted from analyses based on human expertise (rule decisions), classical machine learning algorithms (Random Forest, XGBoost) and quantum-based machine learning algorithms using QSVM. In addition, a hybrid classical-quantum approach is explored by using an ensemble model that combines classical and quantum algorithms to better improve the fraud prevention decision. We found, as expected, that the results highly depend on feature selections and algorithms that are used to select them. The QSVM provides a complementary exploration of the feature space which led to an improved accuracy of the mixed quantum-classical method for fraud detection, on a drastically reduced data set to fit current state of Quantum Hardware.
This paper demonstrates a novel use of quantum machine learning (QML) algorithms for detecting fraudulent activities in the home insurance sector. Utilizing actual data and IBM Quantum processors through the Qiskit software stack, the study introduces an innovative method for selecting quantum features that are specifically designed to accommodate the limitations of Near Intermediate Scale Quantum (NISQ) technology by using the Quantum Support Vector Machine (QSVM) in conjunction with traditional machine learning techniques. A comprehensive comparison was conducted to evaluate their effectiveness in detecting fraud. The indicators such as accuracy, recall, and false positive rate are carefully analyzed. Despite the constraints of current quantum technology, QSVM shows excellent accuracy, especially on limited datasets, indicating its potential to enhance insurance fraud detection. The research emphasizes the crucial feature selection in optimizing QML algorithms for fraud detection tasks. It investigates the capacities of hybrid quantum/classical machine learning ensembles. Future research directions include expanding this study to actual hardware implementations to verify its practical feasibility. The work enhances financial security in the insurance business by using quantum computing technology in fraud detection approaches. It establishes the feasibility and efficacy of using quantum resources to solve difficult real-world issues, setting a foundation for or the broader application of QML in fraud detection and other fields.
The increasing complexity and volume of financial transactions pose significant challenges to traditional fraud detection systems. This technical report investigates and compares the efficacy of classical, quantum, and quantum-hybrid machine learning models for the binary classification of fraudulent financial activities. As of our methodology, first, we develop a comprehensive behavioural feature engineering framework to transform raw transactional data into a rich, descriptive feature set. Second, we implement and evaluate a range of models on the IBM Anti-Money Laundering (AML) dataset. The classical baseline models include Logistic Regression, Decision Tree, Random Forest, and XGBoost. These are compared against three hybrid classic quantum algorithms architectures: a Quantum Support Vector Machine (QSVM), a Variational Quantum Classifier (VQC), and a Hybrid Quantum Neural Network (HQNN). Furthermore, we propose Fraud Detection for Quantum Computing (FD4QC), a practical, API-driven system architecture designed for real-world deployment, featuring a classical-first, quantum-enhanced philosophy with robust fallback mechanisms. Our results demonstrate that classical tree-based models, particularly \textit{Random Forest}, significantly outperform the quantum counterparts in the current setup, achieving high accuracy (97.34%97.34\%97.34%) and F-measure (86.95%86.95\%86.95%). Among the quantum models, \textbf{QSVM} shows the most promise, delivering high precision (77.15%77.15\%77.15%) and a low false-positive rate (1.36%1.36\%1.36%), albeit with lower recall and significant computational overhead. This report provides a benchmark for a real-world financial application, highlights the current limitations of quantum machine learning in this domain, and outlines promising directions for future research.
The increasing dependence on digital and card-based payment systems has heightened the risk of financial fraud. This situation creates an urgent need for models that can identify rare fraudulent events in uneven transaction data. Traditional machine learning models often sacrifice recall for precision when the minority class is very small. Quantum classifiers are theoretically appealing for capturing complex feature relationships, but current hardware limitations on qubit count and circuit depth restrict their effectiveness. This work introduces a hybrid quantum-classical framework for credit card fraud detection. It combines an Extreme Gradient Boosting (XGBoost) classifier with a Quantum Support Vector Machine (QSVM) that uses a ZZ feature map and a fidelity-based quantum kernel. To handle class imbalance, we apply the Synthetic Minority Oversampling Technique (SMOTE) and adjust decision thresholds. The quantum element is trained on a reduced, class-balanced data subset, ensuring it stays within the feasible limits of the simulator. We merge predictions from the classical and quantum models using a weighted probability fusion approach, optimizing the final threshold to maximize the F1-score. Using the Kaggle Credit Card Fraud Detection dataset, the hybrid model achieves a precision of 0.9783, recall of 0.9000, F1-score of 0.9375, and ROC-AUC of 0.9805. It surpasses the standalone XGBoost baseline, XGBoost with SMOTE, and the standalone QSVM regarding F1 and ROC-AUC metrics. These results show that blending classical gradient boosting with quantum kernel-based classification, along with imbalance-aware techniques, can significantly enhance fraud detection quality despite current quantum hardware limitations. This offers a practical path for future work in quantum-assisted financial security.
Every day machine learning in financial systems is increasing with financial institutions taking every steps in their power to detect and block counterfeit transactions. Today, modern electronic payment instruments and financial facilities are becoming more and more susceptible to new methods of fraud which are unobtrusively reproducing the activities of legitimate interests to the detriment of the economy which is losing incalculable sums of money. In order to overcome this the combination technique of quantum and classical methods of calculating the data is a great way to enhance the reliability and accuracy of the fraud detection. It is applied by means of Quantum Support Vector Machine, Variational Quantum Classifier, the classical algorithms of Support Vector Machine and K-Nearest Neighbor with an ensemble based on Quadratic Unconstrained Binary Optimization. These algorithms are used together to scan a stream of transactions in real time and classify what is legitimate behaviour and what is unfavourable behaviour. The work provides evidence to prove that hybrid quantum-classical techniques can improve on the performance of classical systems using improved recall, less false negatives and the speed of detection of new types of frauds. It is shown that the integration of quantum intelligence based upon classical methods of analysis is a powerful and fruitful means to enhance levels of secure financial practice and help combat large scale financial frauds in modern digital environments.
With the rapid growth of digital financial transactions, credit card fraud detection has become a critical challenge in the banking and finance sector. Traditional rule-based systems and classical machine learning (ML) models often struggle to detect complex and evolving fraud patterns, especially in highly imbalanced datasets. This paper proposes a novel hybrid approach to credit card fraud detection using Quantum Machine Learning (QML) techniques combined with classical methods. The system applies Principal Component Analysis (PCA) for dimensionality reduction and Synthetic Minority Oversampling Technique (SMOTE) to handle class imbalance. A classical Random Forest model is implemented as a baseline, while a QML model based on Variational Quantum Circuits (VQC) is developed using PennyLane. A hybrid decision engine combining predictions of both models is designed for improved performance. Experimental results demonstrate that the hybrid model achieves 96.9% accuracy, outperforming individual models by achieving better detection rates and reducing false predictions. The system is deployed via an interactive Streamlit-based dashboard. This work highlights the potential of Quantum Machine Learning in enhancing fraud detection systems in financial security applications.
Quantum algorithms have demonstrated extraordinary potential in numerous fields. The demand for fraud detection in credit cards is growing increasingly, which calls for more efficient algorithms. This work adopts the detection method of Quantum Support Vector Machine (QSVM) to improve the accuracy of credit card fraud detection. Meanwhile, Quantum-Synthetic Minority Oversampling Technique (Quantum-SMOTE) is utilized to address the issue of imbalanced credit card datasets. The QSVM model maps classical data to a high-dimensional Hilbert space through quantum feature mapping, thereby enhancing the separability of features. Then, quantum kernel computation is performed to calculate the inner products between features for model training. The research results show that the QSVM achieves the best overall performance, which indicates that QSVM has significant potential in handling credit card fraud detection.