: In financial systems, abnormal activities in securities transactions pose significant risks due to which there is a requirement of smart and accurate anomaly detection procedures. The presented work in this paper employs a Particle Swarm Optimization (PSO)-tuned Quantum Neural Network (QNN) for anomaly detection. The QNN proposed here is designed using variational quantum circuits to process PSO optimized features and utilises the quantum advantage in neural computing. Performance of the proposed system is evaluated by executing on the IEEE-CIS Fraud Detection dataset. QNN’s weights and biases are optimized by using PSO to enhance capability of the designed network to escape from local optima and to enhance prediction accuracy. The results presented demonstrate the performance of proposed PSO-QNN model and these outcomes are compared with the conventional algorithms- Long Short-Term Memory (LSTM), k-Nearest Neighbours (KNN), and Support Vector Machines (SVM). The work proposed in this paper achieves a precision of 98.55% with improved sensitivity, specificity, recall and attained an impressive Matthews Correlation Coefficient (MCC) of 0.94. As presented in the results, reduced values of FP and FN rates, showcase the reliability of the proposed PSO-QNN model for anomaly detection. For anomaly detection, adopting QNN and optimising it by PSO, represents a significant advancement and this offers a progressive and functional solution for securities transactions in financial systems.
: In financial systems, abnormal activities in securities transactions pose significant risks due to which there is a requirement of smart and accurate anomaly detection procedures. The presented work in this paper employs a Particle Swarm Optimization (PSO)-tuned Quantum Neural Network (QNN) for anomaly detection. The QNN proposed here is designed using variational quantum circuits to process PSO optimized features and utilises the quantum advantage in neural computing. Performance of the proposed system is evaluated by executing on the IEEE-CIS Fraud Detection dataset. QNN’s weights and biases are optimized by using PSO to enhance capability of the designed network to escape from local optima and to enhance prediction accuracy. The results presented demonstrate the performance of proposed PSO-QNN model and these outcomes are compared with the conventional algorithms- Long Short-Term Memory (LSTM), k-Nearest Neighbours (KNN), and Support Vector Machines (SVM). The work proposed in this paper achieves a precision of 98.55% with improved sensitivity, specificity, recall and attained an impressive Matthews Correlation Coefficient (MCC) of 0.94. As presented in the results, reduced values of FP and FN rates, showcase the reliability of the proposed PSO-QNN model for anomaly detection. For anomaly detection, adopting QNN and optimising it by PSO, represents a significant advancement and this offers a progressive and functional solution for securities transactions in 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.
Detection of fraud in money transactions is probably one of the most significant factors in keeping financially systems sound. Conventional machine learning techniques, though as effective as they are, have difficulty identifying sneaky and changing fraud patterns. This study investigates both traditional machine learning methods—such as XGBoost, Support Vector Machines (SVM), and Random Forest—and quantum-inspired methods, such as Quantum Support Vector Machines (Quantum SVM) and Quantum Neural Networks (QNNs), in detecting fraudulent transactions. On the basis of comparing these models' accuracy, precision, and processing time, we would like to establish the superiority of quantum-inspired approaches over traditional approaches. Our findings indicate that Quantum SVM and QNNs offer significant improvements under some circumstances, which indicates the promise of applying ideas from quantum computing towards improving fraud detection ability.
With Deep learning and quantum computing are emerging technologies with transformative potential in financial risk assessment, optimization, and fraud detection. The integration of these fields can significantly enhance the efficiency and accuracy of financial decision-making processes. However, existing fraud detection methods often suffer from high false positives, slow processing times, and limited adaptability to complex fraud patterns. Traditional machine learning models struggle with scalability and computational efficiency when dealing with large-scale financial data. To address these issues, we propose the Quantum-Inspired Neural Networks for Fraud Detection (Q-INN-FD) framework, which leverages quantum-inspired computing principles to enhance neural network architectures. The framework incorporates quantum-inspired feature encoding, variational quantum circuits, and hybrid classical-quantum learning mechanisms to improve pattern recognition in financial transactions. These techniques enable more efficient fraud detection by enhancing model robustness and reducing computational overhead. The proposed method is applied to financial datasets to detect fraudulent transactions, optimize risk assessment models, and improve decision-making in real-time scenarios. Our findings demonstrate that Q-INN-FD achieves higher accuracy, faster processing, and reduced false positive rates compared to traditional deep learning approaches. This paper highlights the potential of quantum-inspired deep learning for revolutionizing financial security and risk management.
Financial markets are complex nonlinear systems characterized by high-dimensional interactions, temporal dependencies, and rapidly evolving asymmetric patterns. Detecting hidden structures and abnormal behaviors in high-frequency financial data remains a challenging problem due to market instability and dynamic uncertainty. This study proposes an innovative quantum neural network (QNN)-based framework for adaptive forecasting and anomaly detection by exploiting quantum representation learning for complex financial systems. The proposed architecture is developed in the Qiskit environment using a hybrid classical-quantum optimization strategy based on a Variational Quantum Circuit (VQC). A quantum feature-mapping mechanism transforms multidimensional financial variables into quantum states, enabling extraction of latent relationships and structural patterns from high-dimensional data. A parameterized quantum circuit is optimized using the ADAM algorithm within a classical-quantum learning loop. The framework consists of two stages: first, multivariate financial dynamics are forecasted using market microstructure, volatility-related, and macroeconomic indicators obtained from the Electronic Data Distribution System (EDDS) of the Central Bank of the Republic of Türkiye; second, deviations between predicted and observed states are analyzed for anomaly identification. Comprehensive experiments on the BIST All-100 Index, trading volume, and monetary indicators demonstrate that the proposed QNN model achieves superior performance compared with ANN, LSTM, Bi-LSTM, LSTM-GRU, CNN, and Transformer-based approaches. The findings indicate that quantum-enhanced learning provides an effective computational framework for modeling complex asymmetric patterns and discovering hidden structures in dynamic systems.
Particle Swarm Optimization (PSO) is a popular algorithm used for optimization problems in various domains. However, the PSO algorithm suffers from some limitations, e.g., premature convergence and slow convergence rate. In this paper, we propose a new algorithm called Quantum Rotation Gate Particle Swarm Optimization (QPSO), which is based on the quantum rotation gate to address these shortcomings. The proposed QPSO algorithm aims to improve the optimization capability of the original PSO. We applied QPSO to optimize the neural network architecture for numerical anomaly detection on the self-noise aerodynamic wind tunnel test data set. Good results are achieved and the effectiveness of the proposed method is demonstrated. Compared to the original PSO algorithm, QPSO outperforms it in terms of convergence rate and accuracy.
Social financial technology focuses on trust, sustainability, and social responsibility, which require advanced technologies to address complex financial tasks in the digital era. With the rapid growth in online transactions, automating credit card fraud detection and loan eligibility prediction has become increasingly challenging. Classical machine learning (ML) models have been used to solve these challenges; however, these approaches often encounter scalability, overfitting, and high computational costs due to complexity and high-dimensional financial data. Quantum computing (QC) and quantum machine learning (QML) provide a promising solution to efficiently processing high-dimensional datasets and enabling real-time identification of subtle fraud patterns. However, existing quantum algorithms lack robustness in noisy environments and fail to optimize performance with reduced feature sets. To address these limitations, we propose a quantum feature deep neural network (QFDNN), a novel, resource efficient, and noise-resilient quantum model that optimizes feature representation while requiring fewer qubits and simpler variational circuits. The model is evaluated using credit card fraud detection and loan eligibility prediction datasets, achieving competitive accuracies of 82.2% and 74.4%, respectively, with reduced computational overhead. Furthermore, we test QFDNN against six noise models, demonstrating its robustness across various error conditions. Our findings highlight QFDNN’s potential to enhance trust and security in social financial technology by accurately detecting fraudulent transactions while supporting sustainability through its resource-efficient design and minimal computational overhead.