Fraud Detection Research Articles

Fund transfer fraud detection: Analyzing irregular transactions and customer relationships with self-attention and graph neural networks

This paper presents a method for identifying fraudulent fund transfers using real bank data, analyzing customer information, transactional activities, and customer relationships. The preprocessing step transforms high-dimensional, irregular transaction time series into regular time series, then further compresses them in a latent space using a self-attention-based autoencoder. To address the scarcity of fraudulent data samples and mitigate training issues caused by data imbalance, various deep generative models, including the conditional variational autoencoder and Wasserstein generative adversarial network, are applied to generate additional fraudulent raw data and augment fraud samples in latent space. The reparameterization trick is integrated into the encoder–decoder structure to boost the model’s generative capabilities. Additionally, a Graph Neural Network (GNN) is used to model customer relationships. The proposed approach utilizes end-to-end learning, integrating the autoencoder’s reconstruction loss, KL divergence loss (when reparameterization trick is applied), and classification loss for fraud detection. To optimize computational resources, neighborhood sampling for GNN is combined with mini-batch training for the autoencoder, improving both training efficiency and model reliability. Comprehensive experiments demonstrate the effectiveness of the proposed fusion network, highlighting the importance of each component and preprocessing step. For example, the areas under the precision–recall curves for fraud detection show notable improvements in our model. For suspicious transactions identified by the bank’s rules, other models range from 0.66% to 22.15%, while our model reached 27%. For non-suspicious transactions, other models range from 2.53% to 22.00%, with our model achieving 22.90%. This model has potential for wider applications in anomaly detection, particularly in datasets with irregular time series and complex customer relationships.

FIAD: Graph anomaly detection framework based feature injection

Anomaly detection on attributed networks is widely used in the real world, such as in spam, and fraud detection. Due to the scarcity of anomaly data in the real world, anomaly detection methods typically use unsupervised techniques to detect anomalies. In recent years, methods based on graph neural networks and autoencoders have performed significantly better than previous methods with injected anomalies. But the current node-based injection methods increase the abnormality of some nodes, which is not conducive to learning more fine-grained anomalous knowledge, appealing to build a more general-purpose anomaly detector. In this paper, we propose a dimension-based method which injects anomalies into feature information by dimension: Feature-Injected Anomaly Detection framework (FIAD). A unique loss function and algorithmic process are developed that significantly enhance the performance by injecting features. Experimental evaluations on seven datasets, comprising four benchmark and three real-world datasets, demonstrate that our proposed method outperforms previous approaches, achieving state-of-the-art results.

An optimized intelligent open-source MLaaS framework for user-friendly clustering and anomaly detection

As data grow exponentially, the demand for advanced intelligent solutions has become increasingly urgent. Unfortunately, not all businesses have the expertise to utilize machine learning algorithms effectively. To bridge this gap, the present paper introduces a cost-effective, user-friendly, dependable, adaptable, and scalable solution for visualizing, analyzing, processing, and extracting valuable insights from data. The proposed solution is an optimized open-source unsupervised machine learning as a service (MLaaS) framework that caters to both experts and non-experts in machine learning. The framework aims to assist companies and organizations in solving problems related to clustering and anomaly detection, even without prior experience or internal infrastructure. With a focus on several clustering and anomaly detection techniques, the proposed framework automates data processing while allowing user intervention. The proposed framework includes default algorithms for clustering and outlier detection. In the clustering category, it features three algorithms: k-means, hierarchical clustering, and DBScan clustering. For outlier detection, it includes local outlier factor, K-nearest neighbors, and Gaussian mixture model. Furthermore, the proposed solution is expandable; it may include additional algorithms. It is versatile and capable of handling diverse datasets by generating separate rapid artificial intelligence models for each dataset and facilitating their comparison rapidly. The proposed framework provides a solution through a representational state transfer application programming interface, enabling seamless integration with various systems. Real-world testing of the proposed framework on customer segmentation and fraud detection data demonstrates that it is reliable, efficient, cost-effective, and time-saving. With the innovative MLaaS framework, companies may harness the full potential of business analysis.

An Overview of Credit Card Fraud Detection Techniques

Credit card fraud is the first thing that comes to mind when the word fraud is uttered. The volume of credit card transactions has increased significantly in recent years, along with a corresponding spike in credit card fraud. Monitoring users' and customers' spending patterns helps detect fraud and stop bad behavior. There is a rising rate of credit card fraud as they become the most widely used payment mechanism for both online and offline transactions. The goal of fraud detection is to identify fraudulent conduct as soon as it is possible and to document it. The utilization of charge cards is normal in present day culture. The multimillion-dollar industry of extortion is growing each. Extortion influences the world economy fundamentally. Different contemporary strategies, for example, information mining, AI, fluffy rationale, hereditary programming, and man-made consciousness, have been produced for identifying charge card extortion. This study tells the best way to successfully consolidate information mining methods to keep a low or high misleading problem rate while accomplishing high extortion inclusion.

Big Data Analytics for Financial Decision Making in Malaysia

Purpose: To aim of the study was to analyze the big data analytics for financial decision making in Malaysia. Methodology: This study adopted a desk methodology. A desk study research design is commonly known as secondary data collection. This is basically collecting data from existing resources preferably because of its low cost advantage as compared to a field research. Our current study looked into already published studies and reports as the data was easily accessed through online journals and libraries. Findings: Big Data Analytics (BDA) significantly enhances financial decision-making in Malaysia by extracting valuable insights from large datasets. It helps improve risk management, customer segmentation, and operational efficiency for financial institutions. BDA enables predictive analysis of market behavior, supports personalized financial services, and enhances fraud detection capabilities. Despite its benefits, challenges like data privacy issues and the need for skilled data professionals persist. Unique Contribution to Theory, Practice and Policy: Diffusion of innovations theory, technology acceptance model (TAM) & network externalities theory may be used to anchor future studies on big data analytics for financial decision making in Malaysia. Prioritize investments in scalable and secure data infrastructure to support the deployment and integration of BDA technologies across financial institutions. This includes upgrading data storage systems, enhancing data processing capabilities, and implementing robust data integration frameworks. Develop and enforce clear regulatory frameworks that govern the ethical use of BDA in financial decision-making. Regulatory guidelines should address data privacy, security standards, transparency in algorithmic processes, and consumer rights protection.

Fraud Detection Based on Credit Review Texts with Dual Channel Memory Networks

ABSTRACT With the rapid development of the automotive finance market in China, fraudulent behaviors present new characteristics such as intellectualization and high concealment. Graph neural networks and memory networks have strong capabilities for processing the textual data containing massive complex associations, providing a new perspective for fraud detection. During the operation of an automotive finance company, a large amount of credit review texts with recording the customers’ multidimensional data are accumulated. These texts contain information that is helpful for risk management, but have not been well explored. In order to effectively identify fraud risks, we propose a fraud detection method based on credit review texts with dual-channel memory network, which combines graph and text memory networks. By utilizing pre-trained language models, the text data for credit review text is encoded into semantic vectors. The graph memory network module and the text memory network module are then employed to extract graph features and text features corresponding to the credit review text. Finally, the generated results from the three modules are fused and input into a classification network to obtain the final determination of financial fraud risk. Comparative experiments with baseline models demonstrate the validity of our model in fraud detection.

Identification and Analysis of Credit Card Fraud Based on Machine Learning Methods

Credit card has become an indispensable payment tool in People's Daily life. However, credit card fraud has also increased, resulting in huge financial losses for banks and individuals. Based on the real world credit card transaction data, this paper uses a variety of machine learning algorithms to identify and analyze credit card fraud. Firstly, the problem of missing and unbalanced data is solved through data preprocessing and feature selection, and important features are screened out, Such as transaction amount, product code, payment card type, etc. Then, integrated logistic regression, random forest, LightGBM, XGBoost, and Stacking models were constructed, and the models were trained and evaluated through cross-validation and parameter optimization. The experimental results show that the integrated Stacking model performs best in credit card fraud detection, with an AUC(Area Under the Curve) value of 0.960, which can accurately identify fraudulent transactions and provide an effective fraud warning mechanism for financial institutions. This mechanism significantly benefits both financial institutions and credit card users by reducing fraud losses and enhancing transaction security. However, it is acknowledged that the study has limitations, including the potential impact of data imbalance on model performance, the need for further testing of model generalization ability to new fraud patterns, and the importance of optimizing real-time performance to ensure practical applicability.

Lipid Marker ESI-MS Method for Quantification of Adulteration in Almond-Based Vegetable Beverage

ABSTRACT Almond-based beverages are valued for their functionalities. However, cases of adulteration are found in the literature aiming to reduce costs. In this study, almond (LA) and peanut (LP)-based beverages were used as investigational controls in commercial products analyzed by gas chromatography and direct infusion electrospray ionization mass spectrometry (ESI-MS) combined with principal component analysis (PCA). Thus, characteristic fatty acids were identified in plant-based beverages. The ESI-MS method combined with PCA indicated individualities regarding the disposition of triacylglycerol (TAG) composition, as higher intensities of TAG were found as a lipid marker at m/z 919 [TAG+NH4]+ of ions formed by arachidic (20:0), 8/heptadecenoic (17:1n-9) and oleic (18:1n-9) fatty acids in LP. The technique demonstrated efficiency in the detection of fraud due to its sensitivity, identifying peanut content in three almond-based commercial beverages (4.4–11.58%). This study highlights the importance of robust analytical methods to the authenticity and quality of food products.

Enhancing fraud detection efficiency in mobile transactions through the integration of bidirectional 3d Quasi-Recurrent Neural network and blockchain technologies

Cases of financial fraud are increasing despite recent technical breakthroughs. It is tough to find authentic financial transaction data due to privacy issues and a lack of inter-organization synergy. However, for technologies based on data, such as machine learning to function accurately inside practical systems, they require actual data. This manuscript proposes a Fraud Detection (FD) Efficiency in Mobile Transactions through the Integration of Bidirectional 3D Quasi-Recurrent Neural Networks and Proof of Voting consensus Blockchain Technologies (Bi-3DQRNN-PoV-FD-MT). A dataset of Bitcoin transactions is employed in the suggested model. The banking sector’s Bitcoin transactions serve as the foundation for this dataset. Then the data balancing is performed using a Self-Adaptive Synthetic Over-Sampling Technique (SASOS). Then, the proposed framework utilizes the Bi-3DQRNN to determine if the information is fraudulent or not. Moreover, an intelligent Enhanced Artificial Gorilla Troops (EAGTO) Optimization algorithm is introduced to tune the weights of the model parameters. A blockchain-based proof of Voting (PoV) consensus algorithm is integrated with the proposed model for forecasting upcoming transactions. The developed scheme is instigated in Python and the performance provides 12.09%, 8.91%, and 6.92% higher accuracy compared with existing techniques like K-nearest neighbor- Distributed Blockchain Consortium (KNN-DBC), Decision tree-Ethereum blockchain-enabled smart contract (DT-EBSC) and Heterogeneous Graph Transformer Networks-Ethereum smart contract (HGTN-ESC).

Rapid and accurate detection of cinnamon oil adulteration in perilla leaf oil using atmospheric solids analysis probe-mass spectrometry

Perilla leaf oil (PLO) is a global premium vegetable oil with abundant nutrients and substantial economic value, rendering it susceptible to potential adulteration by unscrupulous entrepreneurs. The addition of cinnamon oil (CO) is one of the main adulteration avenues for illegal PLOs. In this study, new and real-time ambient mass spectrometric methods were developed to detect CO adulteration in PLO. First, atmospheric solids analysis probe tandem mass spectrometry combined with principal component analysis and principal component analysis-linear discriminant analysis was employed to differentiate between authentic and adulterated PLO. Then, a spectral library was established for the instantaneous matching of cinnamaldehyde in the samples. Finally, the results were verified using the SRM mode of ASAP-MS/MS. Within 3 min, the three methods successfully identified CO adulteration in PLO at concentrations as low as 5% v/v with 100% accuracy. The proposed strategy was successfully applied to the fraud detection of CO in PLO.

Quantum support vector data description for anomaly detection

Abstract Anomaly detection is a critical problem in data analysis and pattern recognition, finding applications in various domains. We introduce quantum support vector data description (QSVDD), an unsupervised learning algorithm designed for anomaly detection. QSVDD utilizes a shallow-depth quantum circuit to learn a minimum-volume hypersphere that tightly encloses normal data, tailored for the constraints of noisy intermediate-scale quantum (NISQ) computing. Simulation results on the MNIST and Fashion MNIST image datasets, as well as credit card fraud detection, demonstrate that QSVDD outperforms both quantum autoencoder and deep learning-based approaches under similar training conditions. Notably, QSVDD requires an extremely small number of model parameters, which increases logarithmically with the number of input qubits. This enables efficient learning with a simple training landscape, presenting a compact quantum machine learning model with strong performance for anomaly detection.

Credit Card Fraud: Analysis of Feature Extraction Techniques for Ensemble Hidden Markov Model Prediction Approach

In the face of escalating credit card fraud due to the surge in e-commerce activities, effectively distinguishing between legitimate and fraudulent transactions has become increasingly challenging. To address this, various machine learning (ML) techniques have been employed to safeguard cardholders and financial institutions. This article explores the use of the Ensemble Hidden Markov Model (EHMM) combined with two distinct feature extraction methods: principal component analysis (PCA) and a proposed statistical feature set termed MRE, comprising Mean, Relative Amplitude, and Entropy. Both the PCA-EHMM and MRE-EHMM approaches were evaluated using a dataset of European cardholders and demonstrated comparable performance in terms of recall (sensitivity), specificity, precision, and F1-score. Notably, the MRE-EHMM method exhibited significantly reduced computational complexity, making it more suitable for real-time credit card fraud detection. Results also demonstrated that the PCA and MRE approaches perform significantly better when integrated with the EHMM in contrast to the conventional HMM approach. In addition, the proposed MRE-EHMM and PCA-EHMM techniques outperform other classic ML models, including random forest (RF), linear regression (LR), decision trees (DT) and K-nearest neighbour (KNN).

Correction to: Fraud Detection Using Machine Learning and Deep Learning

Correction to: Fraud Detection Using Machine Learning and Deep Learning

The role of artificial intelligence in preventing corporate crime

This article explores the novel and transformative role AI plays in enhancing corporate compliance and monitoring to mitigate corporate crime. It delves into how AI technologies, through advanced data analysis and predictive analytics, are revolutionizing the detection and prevention of financial fraud, insider trading, and non-compliance with environmental regulations. The integration of AI into the financial sector is emphasized as pivotal for developing robust fraud prevention algorithms, which analyze vast data volumes to identify malicious activities and prevent financial losses. Moreover, the article probes into the ethical and privacy concerns surrounding the deployment of AI, highlighting the balance needed between efficient crime prevention and safeguarding individual privacy rights. Garcia-Segura's analysis also underscores the need for international cooperation and legal adaptation to uphold ethical standards in AI’s application, ensuring it promotes fairness and justice in combating corporate crime.

PENGARUH PENGALAMAN AUDITOR, SKEPTISME, INTUISI, RISIKO AUDIT DAN KEAHLIAN FORENSIK TERHADAP PENDETEKSIAN KECURANGAN (FRAUD)

This research aims to determine the influence of auditor experience, skepticism, intuition, audit risk, and forensic expertise on fraud detection at Public Accounting Firms in Bandung City. This research is a type of quantitative research. The sampling technique was carried out using purposive sampling technique. So the samples obtained were 11 public accounting offices in Bandung City. The data collection technique used was a questionnaire distribution. The data analysis technique used in this research is multiple linear regression analysis with the SPSS 24 software tool. The results of this research show that auditor experience, skepticism, audit risk and forensic expertise influence fraud detection while intuition has no influence on fraud detection. and simultaneously the auditor's experience, skepticism, intuition, audit risk, and forensic expertise influence fraud detection.Keywords: auditor's experience, skepticism, intuition, audit risk, forensic expertise, and fraud detection.

Bibliometric Analysis of the Machine Learning Applications in Fraud Detection on Crowdfunding Platforms

Bibliometric Analysis of the Machine Learning Applications in Fraud Detection on Crowdfunding Platforms

The effects and potential benefits of audit committee oversight in a strategic setting

AbstractSince the passage of the Sarbanes‐Oxley Act of 2002, many notable frauds have been tied to ineffective audit committee (AC) oversight. As a result, AC oversight is of continuing interest, and regulators continue to debate this issue, garnering a growing body of research focused on the role played by the AC. But little theoretical research exists to guide analytical and empirical researchers investigating AC oversight. The purpose of this study is to provide theoretical guidance by examining AC oversight in a strategic setting. We focus on the AC's role in overseeing internal controls (ICs) and the impact of whether the AC relies on management in designing the controls. We characterize how the nature of control risk changes and how IC strength is associated with the amount of managerial fraud, expected probability of fraud detection (which, on average, equates to audit effort), and audit quality (assessed as 1 − audit risk) across two settings defined by the degree of AC oversight. As one example that highlights the need for theoretical guidance, we consider the literature's presumption that IC strength is negatively associated with audit effort. We find that this association may be positive or negative as IC changes, where the association varies with the degree of direct AC oversight and the change in payoff parameters.

Investigating Credit Card Payment Fraud with Detection Methods Using Advanced Machine Learning

In the cybersecurity industry, where legitimate transactions far outnumber fraudulent ones, detecting fraud is of paramount significance. In order to evaluate the accuracy of detecting fraudulent transactions in imbalanced real datasets, this study compares the efficacy of two approaches, random under-sampling and oversampling, using the synthetic minority over-sampling technique (SMOTE). Random under-sampling aims for fairness by excluding examples from the majority class, but this compromises precision in favor of recall. To strike a balance and ensure statistical significance, SMOTE was used instead to produce artificial examples of the minority class. Based on the data obtained, it is clear that random under-sampling achieves high recall (92.86%) at the expense of low precision, whereas SMOTE achieves a higher accuracy (86.75%) and a more even F1 score (73.47%) at the expense of a slightly lower recall. As true fraudulent transactions require at least two methods for verification, we investigated different machine learning methods and made suitable balances between accuracy, F1 score, and recall. Our comparison sheds light on the subtleties and ramifications of each approach, allowing professionals in the field of cybersecurity to better choose the approach that best meets the needs of their own firm. This research highlights the need to resolve class imbalances for effective fraud detection in cybersecurity, as well as the need for constant monitoring and the investigation of new approaches to increase applicability.

The Effect of Auditor Experience, Client Business Understanding, and Auditor Professional Skepticism on Fraud Detection Ability

The Effect of Auditor Experience, Client Business Understanding, and Auditor Professional Skepticism on Fraud Detection Ability

Online fraud detection: ‘In the moment’ digital accountability in a data-sensitive setting

Online fraud detection: ‘In the moment’ digital accountability in a data-sensitive setting