The field of financial security faces a hard challenge when it comes to detecting credit card fraud because accurate efficient models are required to separate fraudulent transactions from legitimate ones. Most fraud detection systems today utilize deep learning methods supported by Graph Convolutional Networks and Graph Neural Networks. Companies experience several difficulties when implementing these detection methods because they demonstrate poor scale-up potential and high implementation expenses and insufficient accuracy in complex fraud detection tasks. The research presents the Quantum Long Short-Term Memory (QLSTM) model that demonstrates potential for credit card fraud detection purposes. Despite its quantum nature QLSTM optimizes learning functions by advancing representation of data features while speeding up training time. Our model receives evaluation against GNN along with GCN framework using numerous benchmark datasets for fraud detection. Experimental findings indicate that QLSTM delivers superior performance than GNN and GCN at every stage of various measurement benchmarks. The training process of QLSTM achieves near-perfect 99% accuracy after 100 epochs making it outperform GNN and GCN significantly according to our accuracy comparison graph.
The field of financial security faces a hard challenge when it comes to detecting credit card fraud because accurate efficient models are required to separate fraudulent transactions from legitimate ones. Most fraud detection systems today utilize deep learning methods supported by Graph Convolutional Networks and Graph Neural Networks. Companies experience several difficulties when implementing these detection methods because they demonstrate poor scale-up potential and high implementation expenses and insufficient accuracy in complex fraud detection tasks. The research presents the Quantum Long Short-Term Memory (QLSTM) model that demonstrates potential for credit card fraud detection purposes. Despite its quantum nature QLSTM optimizes learning functions by advancing representation of data features while speeding up training time. Our model receives evaluation against GNN along with GCN framework using numerous benchmark datasets for fraud detection. Experimental findings indicate that QLSTM delivers superior performance than GNN and GCN at every stage of various measurement benchmarks. The training process of QLSTM achieves near-perfect 99% accuracy after 100 epochs making it outperform GNN and GCN significantly according to our accuracy comparison graph.
Credit Card Fraud Detection (CCFD) is a major concern for the financial industry, requiring rapid and accurate identification of fraudulent transactions amidst vast datasets. The rapid evolution of quantum computing presents transformative opportunities for enhancing Machine Learning (ML) applications, particularly in the domain of financial security. This paper explores the implementation of Quantum Machine Learning (QML) techniques for CCFD, a critical challenge in the financial industry characterized by imbalanced datasets. Traditional ML models, while effective, often struggle with scalability and computational efficiency when processing large-scale transactional data. QML leverages quantum phenomenon namely entanglement and superposition to potentially outperform classical algorithms in feature extraction and pattern recognition. Our study proposes a hybrid quantumclassical framework, integrating Variational Quantum Circuits (VQC) with classical Neural Networks (NN) to classify fraudulent transactions. Using a simulated quantum environment, we preprocess a publicly available credit card transaction dataset, encoding features into quantum states for processing through a parameterized quantum circuit. The model is trained to improves its ability to detect fraud accurately with fewer false positives, addressing the critical issue of customer inconvenience.
The exponential growth of real-time payment (RTP) systems has agitated on the urgency of robust and efficient fraud detection mechanisms. Traditional machine-learning and rule-based systems often face challenges in processing large, very fast-moving transactional data, which results in delayed detection and substantial financial losses. Quantum computing, with its potential to perform parallel computations on complex probability spaces, offers a novel paradigm to enhance fraud detection. This paper centers on the application of quantum machine learning (QML) techniques—specifically Quantum Graph Neural Networks (QGNNs) and Quantum Support Vector Machines (QSVMs)—over RTP networks for detecting fraudulent activities. This paper will practically implement these hybrid classical and quantum model approaches using Qiskit along with Amazon Braket for datasets such as the IEEE-CIS credit card fraud dataset and quantum synthetically created transaction logs. These models will be compared with classical models in terms of accuracy, precision, recall and execution time. The results demonstrate that quantum-enhanced models offer robust detection accuracy and reduced computational latency, far more effectively when faced with severely imbalanced and nonlinear datasets. Specifically, this study buttresses the quantum forensic financial discipline as it brings to light the reality that quantum computing does not just stay in theoretical promise but can indeed be in practical advantages for scalable, real-time systems for the detection of frauds.
Recent advances in the fields of deep learning and quantum computing have paved the way for innovative developments in artificial intelligence. In this manuscript, we leverage these cutting-edge technologies to introduce a novel model that emulates the intricate functioning of the human brain, designed specifically for the detection of anomalies such as fraud in credit card transactions. Leveraging the synergies of Quantum Spiking Neural Networks (QSNN) and Quantum Long Short-Term Memory (QLSTM) architectures, our approach is developed in two distinct stages, closely mirroring the information processing mechanisms found in the brain's sensory and memory systems. In the initial stage, similar to the brain's hypothalamus, we extract low-level information from the data, emulating sensory data processing patterns. In the subsequent stage, resembling the hippocampus, we process this information at a higher level, capturing and memorizing correlated patterns. We will compare this model with other quantum models such as Quantum Neural Networks among others and their corresponding classical models.
Credit card fraud detection is crucial for financial security which entails identifying unauthorized transactions that can result in significant financial losses. Detection is inherently challenging due to the rarity and indistinguishability of fraudulent transactions from genuine ones, which makes it an anomaly detection problem. Traditional detection systems struggle with the highly imbalanced nature of transaction datasets, where genuine transactions vastly outnumber fraudulent cases. In response to these challenges, we propose a novel detection model utilizing Quantum AutoEncoders-based Fraud Detection (QAE-FD). Our approach leverages quantum computing principles to enhance anomaly detection capabilities by encoding transaction data into compressed quantum states and optimizing the model against a loss function that evaluates the fidelity in flagging fraudulent transactions. The efficacy of the QAE-FD model is tested on a real-world credit card transaction dataset, achieving a G-mean of 0.946 and an AUC of 0.947 which demonstrates superior performance compared to existing models. Our results indicate that QAE-FD has not only higher accuracy in fraud detection but also better computational efficiency. The integration of quantum autoencoders is a promising advancement in the field of anomaly detection for credit card fraud, addressing the limitations of imbalanced datasets and offering a scalable solution for real-time detection systems.
Credit cards are a common form of payment not only because they are extremely convenient to use but also because they are widely accepted. Credit cards are not only very easy to use, but they are also readily available. On account of the fact that it is so widely used, there is a substantial amount of concern regarding the protection of sensitive data from fraudulent activities and access by unauthorised individuals. For the purpose of preserving the trust and confidence of users, it is of the utmost importance to make certain that proper security measures are in place. Quantum machine learning (QML) is gaining popularity for classification applications, and a considerable number of the suggestions that have been made for it involve the utilisation of many qubits. This type of learning is becoming increasingly common. It is essential to make every effort to optimise the efficiency and effectiveness of each qubit before adding additional qubits. This should be done before adding more qubits. This is due to the fact that it is probable that these circuits will not always be able to function effectively in the generation of noisy intermediate-scale quantum (NISQ) systems. By utilising a single qubit, the objective of this research is to provide a description of a novel deep quantum neural network that is designed for classification purposes. In comparison to past studies, this network reduces the number of parameters by replicating various tactics that are frequently utilised in convolutional neural networks (CNNs). This is accomplished by reducing the number of parameters. The modified shuffle frog leaping algorithm, also known as MSFLA, is often utilised in order to decide which traits are the most significant while also lowering the amount of computing that is necessary. The purpose is to validate the concept of the first proposal and offer a tested framework for the later development of the application. This will be accomplished through the demonstration of the classification performance of the architecture that is based on a single qubit. Using a dataset that includes records of credit card transactions done by Europeans, the model is assessed in a setting that is reflective of the real world. This is accomplished by using the dataset. A number of components are included in the technique of the proposed model. These components include data pre-processing, feature engineering, ideal selection, evaluation and evaluation, and evaluation and evaluation. The usage of the computational resources provided by Google Colab allows for the training and testing of the model to be carried out with greater efficiency. When compared to individual classifiers, traditional machine learning approaches, and the model that was recommended, it was discovered that the proposed model was more effective in reducing the obstacles connected with detecting credit card fraud. This concluded that the proposed model was more effective. When compared to earlier models, the model that was suggested has a greater degree of performance in terms of accuracy, precision, recall, and F1-score performance characteristics. This is the case when those parameters are measured. The findings that have been provided here provide a foundation for the creation of fraud detection algorithms that are more resilient and flexible. This is something that will become increasingly required as the number of methods that credit card fraud is committed continues to expand.
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.