Abstract Fraud develops rapidly when transactions happen quickly through electronic pipelines. The traditional fraud detection methods, which are reliable but slow to adapt, cannot keep pace with fraudsters' rapid development of new schemes. They also have trouble adapting to complex relationships and creating explanations that regulators can understand. In this paper, we are proposing a multi-pronged attack on the fraud problem using hybrid quantum-classical techniques. QAFEN-CNN utilizes the concept of adaptive quantum feature entanglement, with volatility-based depth controls to achieve a separation increase of 8%. VQTM-LSTM uses parameterized quantum embeddings as input to each recurrent gate to achieve a 7.9% increase in long-horizon recall. QGCL-Net utilizes quantum enhanced graph construction to model transactional ecosystems, achieving a 12.3% increase in the quality of sub-graphs constructed. Lastly, QVAE-DD proposes a dual-decoder quantum variational autoencoder that generates both input representations and salient explanation representations. The last proposal, QMRL-XAI, utilizes quantum meta-reinforcement learning in combination with counter-factual reasoning to generate policy adaptations after only five episodes. All of these proposals together demonstrate how the use of quantum computing can provide improved accuracy, improve resistance to class imbalance, and produce explanations that can be understood by regulators — a fascinating outline for future applications of quantum computing in anti-fraud analytics.
Abstract Fraud develops rapidly when transactions happen quickly through electronic pipelines. The traditional fraud detection methods, which are reliable but slow to adapt, cannot keep pace with fraudsters' rapid development of new schemes. They also have trouble adapting to complex relationships and creating explanations that regulators can understand. In this paper, we are proposing a multi-pronged attack on the fraud problem using hybrid quantum-classical techniques. QAFEN-CNN utilizes the concept of adaptive quantum feature entanglement, with volatility-based depth controls to achieve a separation increase of 8%. VQTM-LSTM uses parameterized quantum embeddings as input to each recurrent gate to achieve a 7.9% increase in long-horizon recall. QGCL-Net utilizes quantum enhanced graph construction to model transactional ecosystems, achieving a 12.3% increase in the quality of sub-graphs constructed. Lastly, QVAE-DD proposes a dual-decoder quantum variational autoencoder that generates both input representations and salient explanation representations. The last proposal, QMRL-XAI, utilizes quantum meta-reinforcement learning in combination with counter-factual reasoning to generate policy adaptations after only five episodes. All of these proposals together demonstrate how the use of quantum computing can provide improved accuracy, improve resistance to class imbalance, and produce explanations that can be understood by regulators — a fascinating outline for future applications of quantum computing in anti-fraud analytics.
Detecting fraudulent financial transactions is inherently challenging due to extreme class imbalance, complex high-dimensional feature spaces, and the adaptive strategies employed by fraudsters.To overcome these limitations, this work presents a hybrid quantum-classical fraud detection framework that strategically combines conventional machine learning models with quantum computing techniques to enhance predictive reliability.Rich feature representations are constructed by integrating transactional, behavioral, and graph-based attributes to capture both local and relational fraud characteristics.A Quantum Autoencoder (QAE) is utilized to perform efficient dimensionality reduction, enabling compact feature encoding while retaining essential discriminatory patterns.The reduced feature set is subsequently processed using Cat-Boost, alongside Quantum Neural Networks (QNNs) or Variation Quantum Classifiers (VQCs) to leverage complementary learning capabilities.Model outputs are aggregated through a stacking-based meta-classification strategy, resulting in improved generalization and decision stability.Performance evaluation is carried out using fraud-oriented metrics, including recall, precision, accuracy, and false positive rate.Experimental analysis indicates that the proposed hybrid approach consistently surpasses standalone classical and quantum models, achieving superior fraud recall with notably fewer false alarms.These results demonstrate the robustness, scalability, and practical viability of quantum-classical integration, positioning the proposed framework as a promising foundation for next-generation financial fraud detection systems.
Financial transaction systems are becoming increasingly complex and large, in this scenario, fraud detection patterns have become more sophisticated than the conventional detection mechanisms by themselves. While machine learning models have been developed for operational purposes, very few of them are interpretable, sensitive to class imbalance or do not generalize to new fraudulent behaviors. Research on quantum machine learning (QML) for fraud detection is still nascent, with many efforts concentrating on classification without addressing explainability or even attempting to deal with graph-structured and sequential data comprehensively. This study aims to fill this gap by presenting a new explainable quantum machine learning architecture to detect fraud from financial transaction datasets. Three core quantum models are developed and validated: (1) Hybrid Quantum-Loss Adaptive Variational Autoencoder (HQLAVAE) for anomaly detection-has a fidelity aware, class-adaptive loss function that enhances reconstruction of typical transaction patterns and sensitively detects anomalies; (2) The third is Quantum Feature Relevance Graph Attribution (Q-FRGA): an explainable quantum graph neural network particularly capturing transactional relationships with respect to node-level fraud-attributed predictions from Hilbert-space-based relevance scoring; and (3) Quantum Environment-Adaptive Policy Refinement (Q-EAPR), a reinforcement learning model integrating distributional quantum Bellman updates with a novel tracking mechanism for policies to enable online processing of fraud behavior changes. Moreover, two cross-model innovations for enhanced explainability and model integration include Cross-Modal Quantum Counterfactual Explainer (CQCE), generating explainable perturbation-based rationales for single predictions as well as Quantum Residual Explainability-Integrated Ensemble Framework (Q-REIEF) using an ensemble of all models with residual error corrections and meta-explanation tracing sets. This work further advances quantum explainable AI in the areas of transparent, adaptive and high-accuracy fraud detection-all critical gaps in interpretability, data imbalance and behavioral drift on financial systems.
Fraud detection is a Crucial aspect of securing financial systems and protecting against fraudulent activities. This paper presents a new method for Detecting fraud, combining quantum-inspired feature engineering and neural network modeling, which achieves a classification accuracy of 92%, with a precision and recall of 0.92 for non-fraudulent transactions. Utilizing QuantumCircuit from Qiskit, the approach encodes input features into quantum states through angle encoding, improving data representation and capturing complex feature interactions such as entanglement between qubits. The method employs a Quantum Neural Network (QNN) for classifying records and effectively identifying fraudulent transactions. Through real-world dataset experiments, we demonstrate the efficacy of the proposed approach, achieving a precision of 0.65 and recall of 0.68 for fraudulent transactions, while maintaining a false positive rate below 10%. This research leverages advanced machine learning techniques, including balanced sampling strategies to address class imbalance and hyperparameter tuning with Grid-SearchCV for optimal model performance. The paper presents a comprehensive evaluation of the approach, highlighting its strengths in adapting to dynamic and complex environments. Quantum-inspired methods offer the potential to significantly enhance fraud detection systems. However, challenges such as computational complexity and resource requirements remain areas for further investigation. Future research will aim to scale these models for larger datasets and investigate their applicability in fields such as healthcare and e-commerce. In conclusion, our work demonstrates the promising use of quantum-enhanced machine learning for fraud detection. This innovative approach paves the way for developing advanced detection systems that can effectively respond to the evolving landscape of fraudulent activities. Future studies could concentrate on refining these techniques and exploring their potential applications in other areas to further harness the advantages of quantum computing in machine learning.
Detecting financial fraud is a critical aspect of modern intelligent financial systems. Despite the advances brought by deep learning in predictive accuracy, challenges persist-particularly in capturing complex, high-dimensional nonlinear features. This study introduces a novel hybrid quantum recurrent neural network for fraud detection (HQRNN-FD). The model utilizes variational quantum circuits (VQCs) incorporating angle encoding, data reuploading, and hierarchical entanglement to project transaction features into quantum state spaces, thereby facilitating quantum-enhanced feature extraction. For sequential analysis, the model integrates a recurrent neural network (RNN) with a self-attention mechanism to effectively capture temporal dependencies and uncover latent fraudulent patterns. To mitigate class imbalance, the synthetic minority over-sampling technique (SMOTE) is employed during preprocessing, enhancing both class representation and model generalizability. Experimental evaluations reveal that HQRNN-FD attains an accuracy of 0.972 on publicly available fraud detection datasets, outperforming conventional models by 2.4%. In addition, the framework exhibits robustness against quantum noise and improved predictive performance with increasing qubit numbers, validating its efficacy and scalability for imbalanced financial classification tasks.
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.
Financial fraud detection faces unprecedented challenges due to increasing transaction volumes, sophisticated attack vectors, and the need for real-time processing. This paper introduces Adaptive Quantum Entanglement Networks (AQEN), a revolutionary quantum machine learning framework that leverages temporal correlations and dynamic entanglement for superior fraud detection performance. Under Assumptions 1-3 (Section 2), our theoretical analysis predicts asymptotic improvements that can scale exponentially in qubit count compared to naive classical representations for structured temporal models; empirical results validate these gains in realistic simulation regimes We establish rigorous theoretical foundations through novel mathematical frameworks, proving quantum advantage bounds for temporal fraud detection and deriving explicit performance guarantees. The core innovation lies in adaptive entanglement mechanisms that dynamically adjust quantum correlations based on transaction patterns, creating quantum representations that mirror real-world fraud network structures. Experimental validation on comprehensive financial datasets demonstrates that AQEN achieves 94.7% accuracy, 81.2% precision, and 79.8% recall, representing significant improvements over classical state-of-the-art methods (93.5% accuracy, 78.5% precision, 74.2% recall for XGBoost). Statistical analysis confirms the improvements are highly significant (p < 0.001), with AQEN achieving AUC = 0.951 compared to 0.923 for the best classical approach. The paper provides complete algorithmic specifications, quantum circuit implementations, and comprehensive performance analysis, establishing AQEN as a breakthrough approach for next-generation fraud detection systems with practical deployment potential on nearterm quantum devices.