Fraud Detection Methods Research Articles

REPRESENTING FINE GRINED CO-OCCURANCES FOR BEHAVIOR BASED FRAUD DETECTION IN ONLINE SYSTEM

The vigorous development of e-commerce breeds cybercrime. Online payment fraud detection, a challenge faced by online service, plays an important role in rapidly evolving e-commerce. Behavior-based methods are recognized as a promising method for online payment fraud detection. However, it is a big challenge to build highresolution behavioral models by using low-quality behavioral data. In this work, we mainly address this problem from data enhancement for behavioral modeling. We extract fine-grained co-occurrence relationships of transactional attributes by using a knowledge graph. Furthermore, we adopt the heterogeneous network embedding to learn and improve representing comprehensive relationships. Particularly, we explore customized network embedding schemes for different types of behavioral models, such as the population-level models, individual-level models, and generalized-agentbased models. The performance gain of our method is validated by the experiments over the real dataset from a commercial bank. It can help representative behavioral models improve significantly the performance of online banking payment fraud detection. To the best of our knowledge, this is the first work to realize data enhancement for diversified behavior models by implementing network embedding algorithms on attribute-level co-occurrence relationships.

Hyperspectral identification of oil adulteration using machine learning techniques

Food adulteration is a global concern, drawing attention from safety authorities due to its potential health risks. Detecting and categorizing oil adulteration is crucial for consumer safety and food industry integrity. This research explores hyperspectral imaging (HSI) analysis to identify substandard oil adulteration at different stages. Using the non-destructive HSI Specim Fx 10 system, a method for precise and easy imaging-based fraud detection and classification was proposed. The 670 oil samples, including pure (Almond, Mustard, Coconut, Olive) and adulterated (Sunflower, Castor, Liquid Paraffin), were analyzed. The Savitzky-Golay filter preprocessed the images to remove noise and smooth spectral signatures. The oils were identified using various machine learning approaches, including Support Vector Machines, Logistic Regression, Linear Discriminant Analysis, Random Forests, Decision Trees, K-Nearest Neighbors, and Naïve Bayes with Linear Discriminant Analysis excelling in identification. Performance parameters, including precision, recall, F1-score, and overall accuracy, were calculated. The proposed method achieved a validation accuracy of 100%, outperforming numerous state-of-the-art approaches. This study introduces a robust pipeline for effective oil adulteration detection, offering a significant advancement in food safety and quality control.

FORENSIC ACCOUNTING RESEARCH TRENDS: A COMPREHENSIVE REVIEW OF KEY THEMES AND FUTURE DIRECTIONS

This study explores the evolving landscape of forensic accounting research (FAR) through a combined content and bibliometric analysis. Utilizing the Scopus database and focusing on publications from 1991 to 2023, and further analysed 16 literature reviews to extract key themes and trends, we identified key research themes and trends within FAR. Our analysis reveals a shift towards technology-driven fraud detection and prevention methods, emphasizing the use of data analytics, artificial intelligence, and blockchain. Additionally, there is a growing recognition of the human element in fraud, prompting research into behavioural and psychological factors influencing fraudulent activities. The study also highlights the need for standardized forensic accounting education and training programs to equip professionals with the necessary skills to combat increasingly sophisticated financial crimes. Addressing regional disparities in expertise and fostering international collaboration are crucial for advancing the field and promoting global financial integrity. This research provides valuable insights for academics, practitioners, and policymakers seeking to understand current trends and future directions within FAR.

A fraud detection method based on integrated machine learning

A fraud detection method based on integrated machine learning

Research on Photovoltaic Index Insurance Fraud Detection Method Based on LSTM-AR Model

Research on Photovoltaic Index Insurance Fraud Detection Method Based on LSTM-AR Model

A Credit Card Fraud Detection Method Based on Mahalanobis Distance Hybrid Sampling and Random Forest Algorithm

A Credit Card Fraud Detection Method Based on Mahalanobis Distance Hybrid Sampling and Random Forest Algorithm

ATTRACTING INNOVATIVE ARTIFICIAL INTELLIGENCE TOOLS TO THE CRYPTOCURRENCY MARKET

The purpose of the article is to conduct a study and determine the importance and benefits of using artificial intelligence (AI) tools for certain areas of the cryptocurrency market, in particular, detecting and preventing fraud in the cryptocurrency market, as well as the possibilities of using AI chatbots in trading and in the formation of investment portfolios. The article covers the analysis of the growth of digital currencies and the increasing number of hacker attacks, defines the role of AI in ensuring security, considers methods of fraud detection and prevention, and analyses development prospects. AI plays a crucial role in identifying suspicious transactions and preventing fraud. The study aims to investigate the benefits and potential risks of AI bots. AI's integration has transformed the market, enabling more informed decision-making, improved investment strategies, and higher returns. The article emphasizes the need for ongoing research into the evolving landscape of AI in cryptocurrency, discussing challenges, and the potential to finance sphere. The integration of AI in fraud detection has proven advantageous, enabling real-time data analysis and pattern recognition, enhancing security for investors. The article also addresses concerns such as algorithmic bias and the displacement of traders and using AI chat bots. While acknowledging the risks, it highlights the positive impact of AI on efficiency, reliability, and security in the cryptocurrency marketThe article presents an algorithmisation of the possibilities and procedures for engaging artificial intelligence in the fight against fraud, as well as recommendations for market participants and regulators. The presented results highlight the existing innovative potential of AI to improve the security and efficiency of the functioning of participants in the cryptocurrency market. Overall, the article suggests that AI's transformative influence in the cryptocurrency market is a game changer, shaping the industry's future and presenting opportunities for growth and innovation.

Detection of E-Commerce Fraud Review via Self-Paced Graph Contrast Learning

Abstract Recently, graph neural networks (GNNs) have been widely used for e-commerce review fraud detection by aggregating the neighborhood information of nodes in various relationships to highlight the suspiciousness of nodes. However, existing GNN-based detection methods are susceptible to sample class imbalance and fraud camouflage problems, resulting in poor quality of constructed graph structures and inability to learn reliable node embeddings. To address the above problems, we propose a novel e-commerce review fraud detection method based on self-paced graph contrast learning (SPCL-GNN). Firstly, the method constructs a subgraph by initially selecting nodes through a labeled balanced extractor. Secondly, the subgraph connections are filtered and complemented by combining self-paced graph contrast learning and an adaptive neighbor sampler to obtain an optimized graph structure. Again, an attention mechanism is introduced in intra- and inter-relationship aggregation to focus on the importance of aggregation under different relationships. Finally, the quality of the node embedding representation is further improved by maximizing the mutual information between the local and global representations. Experimental results on the Amazon and YelpChi datasets show that SPCL-GNN significantly outperforms the baseline.

Differences in business fraud between state-owned and private companies: case of Croatia

Abstract Fraud presents a serious problem and arising issue for all of society at national and global levels. According to global fraud research conducted by the Association of Certified Fraud Examiners, it is estimated that the average company loses about 5% of its annual revenue due to different types of business fraud. Total estimated annual fraud losses according to global ACFE research reaches about 4.7 trillion dollars. Business frauds also present an important issue for the Croatian economy, business community and society as a whole. Thereby, considerable attention should be given to this issue with the aim of raising awareness throughout society on fraud and its negative and destructive impact on all of society. The main purpose of this paper is to examine differences in fraud characteristics between state-owned and private companies in the Republic of Croatia. Research was based on data on business frauds obtained by the Association of Certified Fraud Examiners Croatia which included 124 respondents. Data were related to frauds that occurred in Croatian companies in 2021 and 2020. In this paper we focused on fraud characteristics such as fraud loss, type of fraud, fraud duration and methods of fraud detection in order to determine whether fraud in privately owned companies differs significantly from fraud in state-owned companies. Research results revealed how differences in fraud characteristics among privately and state-owned companies exist. Based on a sample of Croatian companies that were victims of fraud, it is noted how fraud in state-owned companies lasts longer and creates greater loses in comparison to fraud in private owned companies. Moreover, data related to estimated fraud loss and fraud duration were statistically significant in terms of differentiating these two groups of companies. Based on data on discriminatory variables a logistic regression model correctly classified 78.46% of companies in the group of companies that are privately or state-owned.

Ensemble learning based health care claim fraud detection in an imbalance data environment

<p><span>Healthcare fraud has become a common encounter in the healthcare finance industry. The financial security of healthcare payers and providers is seriously impacted by healthcare fraud. When incorrect or exaggerated medical services are invoiced for reimbursement, fraudulent healthcare claims result. The effective operation of the healthcare system depends on the detection of such fraudulent actions. This paper develops a healthcare claim fraud detection method based on ensemble learning. Stack ensemble learning algorithm performance is compared to that of methods such as multi-layer perceptron (MLP) classifier, support vector classifier (SVC), logistic regression (LR), and decision tree (DT) algorithm. Because of the healthcare data imbalance, the normal transaction is significantly higher than the fraudulent transaction. The machine learning (ML) algorithm performs poorly because imbalanced data causes it to be biased toward the majority class. As a result, the data is unsampled using the synthetic minority oversampling technique (SMOTE) technique to provide balanced data. The experimental results show that for the identification of healthcare claim fraud, the ensemble learning strategy greatly <span>outperforms single learning algorithms. The stack ensemble learning outperforms all the area under the curve for the receiver-operating characteristic (AUC ROC) curves from various algorithms, and the AUC-ROC curve is determined to be producing results that are adequate for all approaches.</span></span></p>

Feature difference-aware graph neural network for telecommunication fraud detection

With the continuous escalation of telecommunication fraud modes, telecommunication fraud is becoming more and more concealed and disguised. Existing Graph Neural Networks (GNNs)-based fraud detection methods directly aggregate the neighbor features of target nodes as their own updated features, which preserves the commonality of neighbor features but ignores the differences with target nodes. This makes it difficult to effectively distinguish fraudulent users from normal users. To address this issue, a new model named Feature Difference-aware Graph Neural Network (FDAGNN) is proposed for detecting telecommunication fraud. FDAGNN first calculates the feature differences between target nodes and their neighbors, then adopts GAT method to aggregate these feature differences, and finally uses GRU approach to fuse the original features of target nodes and the aggregated feature differences as the updated features of target nodes. Extensive experiments on two real-world telecom datasets demonstrate that FDAGNN outperforms seven baseline methods in the majority of metrics, with a maximum improvement of about 5%.

Bank Loan Fraud Detection with Integrated KYC Verification System

In today's technologically-driven financial landscape, bank loan fraud poses a significant threat to both financial institutions and their customers. While traditional methods of fraud detection have been moderately effective, the increasing sophistication of fraudsters necessitates the implementation of more advanced measures. This research proposes an integrated system for bank loan fraud detection that leverages the robustness of Know Your Customer (KYC) verification. By combining traditional KYC processes with advanced machine learning algorithms, this system seeks to provide a more comprehensive approach to detecting and preventing fraudulent loan applications. Initial results indicate a marked reduction in successful fraud attempts, as well as a decrease in false positives compared to conventional systems. Furthermore, the integrated system offers enhanced customer experience by streamlining the loan application process, reducing verification times, and ensuring greater security of personal data. As financial institutions continue to grapple with the challenges of fraud, this research underscores the importance of integrating traditional verification methods with cutting-edge technological solutions for optimal results

Detection of Authentication of Meat Products by Low Cost Closed-tube Molecular Methods

Nowadays adulteration of meat products, especially of ground meat products which form an easy case scenario for implementing adulteration practices due to their structure and texture, emerges a critical issue of raised concern threatening fair trade, food quality and consumers’ health and protection. Food authentication testing is the tool to address this kind of fraud. There is several analytical methodologies applied for meat authentication targeting at different biomarkers and using a variety of analytical techniques. However, the applied methodologies should exhibit suitable performance characteristics such as reliability, sensitivity, reproducibility and availability in order to be fit for purpose. During the last 20 years, amplification tests have emerged as an important diagnostic tool, not only for clinical applications, but also for food quality and safety. It was urgent to develop molecular techniques fast and sensitive. The introduction of new DNA technologies has facilitated the ease and accuracy of of methods for fraud detection. The closed-tube methods of Loop-mediated isothermal amplification (LAMP) and Gold Nanoparticles linked with oligonucleotides used as molecular probes are well known for their robust and highly sensitive and specific amplification of target DNA. Moreover, these techniques are rapid, low-cost diagnostics and available on site. This review provides a comprehensive overview of the molecular methods developed that can be applied for investigating ground meat adul-teration and focuses on the advantages of the rapid closed tube methods that can yield color results interpreted with the naked eye. The application of such time- and cost-effective molecular tools in the food market is proposed to provide a first-level filter for meat adulterated products, serving as a complementary tool to the more in-depth -omics approach.

Beyond the individual: An improved telecom fraud detection approach based on latent synergy graph learning

The development of telecom technology not only facilitates social interactions but also inevitably provides the breeding ground for telecom fraud crimes. However, telecom fraud detection is a challenging task as fraudsters tend to commit co-fraud and disguise themselves within the mass of benign ones. Previous approaches work by unearthing differences in calling sequential patterns between independent fraudsters, but they may ignore synergic fraud patterns and oversimplify fraudulent behaviors. Fortunately, graph-like data formed by traceable telecom interaction provides opportunities for graph neural network (GNN)-based telecom fraud detection methods. Therefore, we develop a latent synergy graph (LSG) learning-based telecom fraud detector, named LSG-FD, to model both sequential and interactive fraudulent behaviors. Specifically, LSG-FD introduces (1) a multi-view LSG extractor to reconstruct synergy relationship-oriented graphs from the meta-interaction graph based on second-order proximity assumption; (2) an LSTM-based calling behavior encoder to capture the sequential patterns from the perspective of local individuals; (3) a dual-channel based graph learning module to alleviate the disassortativity issue (caused by the camouflages of fraudsters) by incorporating the dual-channel frequency filters and the learnable controller to adaptively aggregate high- and low-frequency information from their neighbors; (4) an imbalance-resistant model trainer to remedy the graph imbalance issue by developing a label-aware sampler. Experiment results on the telecom fraud dataset and another two widely used fraud datasets have verified the effectiveness of our model.

Investigating the effectiveness of one-class and binary classification for fraud detection

Research into machine learning methods for fraud detection is of paramount importance, largely due to the substantial financial implications associated with fraudulent activities. Our investigation is centered around the Credit Card Fraud Dataset and the Medicare Part D dataset, both of which are highly imbalanced. The Credit Card Fraud Detection Dataset is large data and contains actual transactional content, which makes it an ideal benchmark for credit card fraud detection. The Medicare Part D dataset is big data, providing researchers the opportunity to examine national trends and patterns related to prescription drug usage and expenditures. This paper presents a detailed comparison of One-Class Classification (OCC) and binary classification algorithms, utilizing eight distinct classifiers. OCC is a more appealing option, since collecting a second label for binary classification can be very expensive and not possible to obtain within a reasonable time frame. We evaluate our models based on two key metrics: the Area Under the Precision-Recall Curve (AUPRC)) and the Area Under the Receiver Operating Characteristic Curve (AUC). Our results show that binary classification consistently outperforms OCC in detecting fraud within both datasets. In addition, we found that CatBoost is the most performant among the classifiers tested. Moreover, we contribute novel results by being the first to publish a performance comparison of OCC and binary classification specifically for fraud detection in the Credit Card Fraud and Medicare Part D datasets.

CTCN: a novel credit card fraud detection method based on Conditional Tabular Generative Adversarial Networks and Temporal Convolutional Network.

Credit card fraud can lead to significant financial losses for both individuals and financial institutions. In this article, we propose a novel method called CTCN, which uses Conditional Tabular Generative Adversarial Networks (CTGAN) and temporal convolutional network (TCN) for credit card fraud detection. Our approach includes an oversampling algorithm that uses CTGAN to balance the dataset, and Neighborhood Cleaning Rule (NCL) to filter out majority class samples that overlap with the minority class. We generate synthetic minority class samples that conform to the original data distribution, resulting in a balanced dataset. We then employ TCN to analyze transaction sequences and capture long-term dependencies between data, revealing potential relationships between transaction sequences, thus achieving accurate credit card fraud detection. Experiments on three public datasets demonstrate that our proposed method outperforms current machine learning and deep learning methods, as measured by recall, F1-Score, and AUC-ROC.

An intelligent approach for anomaly detection in credit card data using bat optimization algorithm

As technology advances, many people are utilising credit cards to purchase their necessities, and the number of credit card scams is increasing tremendously. However, illegal card transactions have been on the rise, costing financial institutions millions of dollars each year. The development of efficient fraud detection techniques is critical in reducing these deficits, but it is difficult due to the extremely unbalanced nature of most credit card datasets. As compared to conventional fraud detection methods, the proposed method will help in automatically detecting the fraud, identifying hidden correlations in data and reduced time for verification process. This is achieved by selecting relevant and unique features by using Bat Optimization Algorithm (BOA). Next, balancing is performed in the highly imbalanced credit card fraud dataset using Synthetic Minority over-sampling technique (SMOTE). Then finally the CNN model for anomaly detection in credit card data is built using full center loss function to improve fraud detection performance and stability. The proposed model is tested with Kaggle dataset and yields around 99% accuracy.

An Intelligent Machine Learning Approach for Fraud Detection in Medical Claim Insurance: A Comprehensive Study

Medical claim insurance fraud poses a significant challenge for insurance companies and the healthcare system, leading to financial losses and reduced efficiency. In response to this issue, we present an intelligent machine- learning approach for fraud detection in medical claim insurance to enhance fraud detection accuracy and efficiency. This comprehensive study investigates the application of advanced machine learning algorithms for identifying fraudulent claims within the insurance domain. We thoroughly evaluate several candidate algorithms to select an appropriate machine learning algorithm, considering the unique characteristics of medical claim insurance data. Our chosen algorithm demonstrates superior capabilities in handling fraud detection tasks and is the foundation for our proposed intelligent approach. Our proposed approach incorporates domain knowledge and expert rules, augmenting the machine learning algorithm to address the intricacies of fraud detection within the insurance context. We introduce modifications to the algorithm, further enhancing its performance in detecting fraudulent medical claims. Through an extensive experimental setup, we evaluate the performance of our intelligent machine-learning approach. The results indicate significant accuracy, precision, recall, and F1-score improvements compared to traditional fraud detection methods. Additionally, we conduct a comparative analysis with other machine learning algorithms, affirming the superiority of our approach in this domain. The discussion section offers insights into the interpretability of the experimental findings and highlights the strengths and limitations of our approach. We conclude by emphasizing the significance of our research for the insurance industry and the potential impact on the healthcare system's efficiency and cost-effectiveness.

Credit Card Fraud Detection for Contemporary Financial Management Using XGBoost-Driven Machine Learning and Data Augmentation Techniques

The rise of digital transactions and electronic payment systems in modern financial management has brought convenience but also the challenge of credit card fraud. Traditional fraud detection methods are struggling to cope with the complexities of contemporary fraud strategies. This study explores the potential of machine learning, specifically the XGBoost (eXtreme Gradient Boosting) algorithm, combined with data augmentation techniques, to enhance credit card fraud detection. The research demonstrates the effectiveness of these techniques in addressing imbalanced datasets and improving fraud detection accuracy. The study showcases a balanced approach to precision and recall in fraud detection by leveraging historical transaction data and employing techniques like Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors (SMOTE-ENN). The implications of these findings for contemporary financial management are profound, offering the potential to bolster financial integrity, allocate resources effectively, and strengthen customer trust in the face of evolving fraud tactics.

A Novel Method of Fraud Detection of Credit Cards by Fuzzy, LSTM, and PSO Optimization

Since online shopping has become so popular, credit card theft has skyrocketed. This makes it hard to spot fake charges on accounts. In this research, credit card fraud detection is performed using a fuzzy database. It has been considered a data mining challenge to reliably identify whether or not a transaction is legitimate. This paper discusses the LSTM method and fuzzy logic. The learning process was sped up and made more precise by using a technique called particle swarm optimization (PSO). Performance values have been compared with those of the LSTM and fuzzy logic techniques, and a PSO-based neural network has been intensively trained by increasing the number of iterations and the population, or number of swarms. It has been shown that the PSO-based algorithm yields the best result for detecting fraudulent transactions. The goal of this method is to lower the mean square error (MSE) rate of the system. PSO is a popular optimization technique that can be used to locate the optimal set of features for the credit card fraud detection system. The proposed method PSO shows less mean squared error compared with Fuzzy and LSTM techniques.