Fraud Detection Research Articles

Effective fraud detection in e-commerce: Leveraging machine learning and big data analytics

Sophisticated cyber-infrastructure and information technology methods are necessary to exploit and analyse the massive amounts of data generated by online transactions. This study introduces a big data platform for online retailers to tackle various issues in the e-commerce industry. Both people and businesses are vulnerable to fraud, which is a worldwide problem. In today's tech-driven society, the battle against fraud has been greatly aided by machine learning (ML) and artificial intelligence (AI). This essay takes a look at the conventional wisdom about fraud prevention and shows how outdated it is when compared to modern fraud techniques. It delves further into the ways in which ML and AI are supporting fast digitization, which in turn revolutionises fraud prevention efforts. Machine learning and artificial intelligence algorithms enable companies to comb through massive amounts of data for patterns and anomalies that could suggest fraudulent activity. In this article, we will explore how machine learning and artificial intelligence may greatly enhance fraud prevention efforts. These technologies can help with advanced data analytics, anomaly detection, and predictive modelling. The text highlights the ways in which these technologies empower organisations to proactively identify and reduce fraud risks, protecting both their operations and stakeholders.

A GNN-based fraud detector with dual resistance to graph disassortativity and imbalance

With the prosperity of Internet services, various fraudulent activities have emerged, and some graph neural network-based methods have been proposed for fraud detection. These methods have achieved significant performances based on the assortativity assumption where the connected nodes tend to have the same labels. However, the fraud graphs are not always assortative but more likely disassortative as fraudsters usually disguise themselves by deliberately making extensive connections to benign users. Furthermore, some studies have noticed node imbalance issues as the fraudsters are far fewer than normal users. But for another one, the edge imbalance issue is unexplored, and they also failed to make full use of these rare but valuable edges. Therefore, we propose an imbalanced disassortative graph learning framework for fraud detection. Specifically, a learnable dual-channel graph convolution filter is introduced to adaptively aggregate low- and high-frequency signals from its neighbors to assimilate/discriminate nodes with assortative/disassortative edges. Then, the label-aware node and edge samplers are designed to remedy graph imbalance problems. Furthermore, the sampled edges are treated as the auxiliary supervision signal to explicitly facilitate the training of graph filters. Extensive experiments on real-world datasets verify the superiority of our method.

Determinants influencing fraud detection: Role of internal auditors’ quality

Frequent occurrences of fraud take place due to poor fraud prevention and detection. The purpose of this study is to ascertain the impact of internal audit effectiveness and continued professional commitment to fraud detection with internal auditors’ quality as a moderating variable. Seventy-eight questionnaires were distributed to internal auditors and supervisors at the Inspectorate of Riau City, Indonesia, who had at least two years of experience. Structural equation modeling (SEM) 3.0 software was used for the data analysis. According to the study’s findings, the effectiveness of internal control (β = –0.932; p < 0.05) and the effectiveness of internal auditors (β = 1.149; p < 0.05) both have an impact on fraud detection. However, ongoing professional commitment (β = 0.069; p > 0.05) has no impact. Quality of internal auditors does not affect the relationship between the effectiveness of internal audits (β = –0.190; p > 0.05), the effectiveness of internal control (β = 0.114; p > 0.05), continued professional commitment (β = 0.018; p > 0.05), and fraud detection. The findings of this study can be used as guidance for management to enhance the performance of internal auditors and for considerations and assessments for fraud detection in the public sector.

Implementation of Credit Card Fraud Detection

The issue of credit card fraud presents a notable concern within the financial sector, leading to considerable finacial losses for both financial institutions and consumers. To address this challenge, this study investigates the application of machine learning methods for detecting credit card fraud. We explore the performance of diverse machine learning algorithms on an actual dataset and suggest an ensemble-based approach that harnesses the strengths of multiple models. Our experimental outcomes demonstrate the effectiveness of machine learning in accurately identifying fraudulent transactions while minimizing false positives.

Advanced Techniques for Fraud Detection in Online Transactions: Leveraging AI and Machine Learning Approaches

Advanced Techniques for Fraud Detection in Online Transactions: Leveraging AI and Machine Learning Approaches

Explainable AI in Credit Card Fraud Detection: Interpretable Models and Transparent Decision-making for Enhanced Trust and Compliance in the USA

Credit Card Fraud presents significant challenges across various domains, comprising, healthcare, insurance, finance, and e-commerce. The principal objective of this research was to examine the efficacy of Machine Learning techniques in detecting credit card fraud. Four key Machine Learning techniques were employed, notably, Support Vector Machine, Logistic Regression, Random Forest, and Artificial Neural Network. Subsequently, model performance was evaluated using Precision, Recall, Accuracy, and F-measure metrics. While all models demonstrated high accuracy rates (99%), this was largely due to the dataset's size, with 284,807 attributes and only 492 fraudulent transactions. Nevertheless, accuracy solely did not provide a comprehensive comparison metric. Support Vector Machine showed the highest recall (89.5), correctly identifying the most positive instances, highlighting its efficacy in detecting true positives. On the other hand, the Artificial Neural Network model exhibited the highest precision (79.4, indicating its capability to make accurate identifications, making it proficient in optimistic predictions.

Machine Learning Models for Fraud Detection: A Comprehensive Review and Empirical Analysis

An in-depth familiarity with ML and DL models for fraud detection is essential due to the growing frequency and complexity of fraudulent activity across many domains. Despite the abundance of research on the subject, empirical analyses of these models, especially in their real-time implementations, are typically lacking. This study fills that need by meticulously reviewing and analysing ML and DL models developed for fraud detection. We draw attention to the shortcomings of existing approaches, which are crucial in the ever-changing field of fraud detection and include problems with recall, scalability, complexity, precision, and accuracy. By evaluating various ML and DL models using these measures, our evaluation method is based on a rigorous empirical approach. Provided that insights into the practical consequences as well as flexibility of each model in real-time circumstances, they thoroughly assess their performance. There are many ways in which this work will be useful; for example, it will help professionals choose the best models for their fraud detection needs, improve academic knowledge of these models in practice, and open the door to more studies that will concentrate on developing better fraud detection tools. This comprehensive research gives academics and companies a foundation for better, more effective and more scalable fraud detection systems in this period of essential digital security.

The Influence of Treasury Single Account Implementation on Public Sector Performance: A Case Study of Selected Parastatals in South East Nigeria (2010-2019)

This study delved into the effect of Treasury Single Account (TSA) on public sector performance in selected parastatals in South East Nigeria (2010-2019). The broad objective of this study was to ascertain the effect of Treasury Single Account (TSA) on public sector performance in selected parastatals in South East Nigeria. Consequently, four research questions and four hypotheses were formulated to guide the study. Survey design was adopted for the study. Area of the study is South East Nigeria, population of the study was 1,548 staff drawn from Boards of Internal Revenues (BIRs) of the five States in South East. Stratified random sampling was used to derive 713 respondents for the study. Instrument for data collection was self-structured questionnaire. Mean and standard deviation was used to answer research questions while ANOVA and Z-test statistic was used to analyze hypotheses. The result based on empirical analysis revealed that treasury single account had positive effect on fraud detection in Parastatals in South East Nigeria, treasury single account had positive effect on revenue mobilization in Parastatals in South East Nigeria, treasury single account had positive effect on blockage of financial leakages in Parastatals in South East Nigeria and treasury single account had positive effect on financial savings in Parastatals in South East Nigeria. Thus, the study concluded that fraud detection, revenue mobilization, financial leakages and financial savings have been affected in Parastatals in South East Nigeria as result of Treasury single account (TSA). Based on the findings, the following recommendations among others were proffered: Government should ensure timely release of operational funds to encourage MDAs to support the TSA Policy. This can be achieved through the use of treasury bills (T-bills) or other short-term borrowing instruments aimed at offsetting the impact of TSA implementation on government cash flows and there should be full implementation of TSA in all states ministries, Departments and Agencies (MDAs). Partial implementation in many states as was observed by the researcher during field work should be discouraged. The gains of TSA cannot be overemphasized. Keywords: Treasury Single Account, Accountability, Public Sector, Revenue, Savings, Parastatatal.

Enhancing fraud detection in banking by integration of graph databases with machine learning

The banking sector's shift from traditional physical locations to digital channels has offered customers unprecedented convenience and increased the risk of fraud for customers and institutions alike. In this study, we discuss the pressing need for robust fraud detection & prevention systems in the context of evolving technological environments. We introduce a graph-based machine learning model that is specifically designed to detect fraudulent activity in various types of banking operations, such as credit card transactions, debit card transactions, and online banking transactions. This model uses advanced methods for anomalies, behaviors, and patterns to analyze past transactions and user behavior almost immediately. We provide an in-depth methodology for evaluating fraud detection systems based on parameters such as Accuracy Recall rate and False positive rate ROC curves. The findings can be used by financial institutions to develop and enhance fraud detection strategies as they demonstrate the effectiveness and reliability of the proposed approach. This study emphasizes the critical role that innovative technologies play in safeguarding the financial sector from the ever-changing strategies of fraudsters while also enhancing banking security.•This paper aims to implement the detection of fraudulent transactions using a state-of-the-art Graph Database approach.•The relational graph of features in the dataset used is modelled using Neo4J as a graph database.•Applying JSON features from the exported graph to various Machine Learning models, giving effective outcomes.

Ai in Fraud Detection: Evaluating the Efficacy of Artificial Intelligence in Preventing Financial Misconduct

AI is anticipated to enhance competitive advantages for financial organisations by increasing efficiency through cost reduction and productivity improvement, as well as by enhancing the quality of services and goods provided to consumers. AI applications in finance have the potential to create or exacerbate financial and non-financial risks, which could result in consumer and investor protection concerns like biassed, unfair, or discriminatory results, along with challenges related to data management and usage. The AI model's lack of transparency may lead to pro-cyclicality and systemic risk in markets, posing issues for financial supervision and internal governance frameworks that may not be in line with a technology-neutral regulatory approach. The primary objective of this research is to explore the effectiveness of Artificial Intelligence in preventing financial misconduct. This study extensively examines sophisticated methods for combating financial fraud, specifically evaluating the efficacy of Machine Learning and Artificial Intelligence. When examining the assessment metrics, this study utilized various metrics like accuracy, precision, recall, F1 score, and the ROC-AUC. The study found that Deep Learning techniques such as “Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks /Long Short-Term Memory, and Auto encoders” achieved high precision and AUC-ROC scores in detecting financial fraud. Voting classifiers, stacking, random forests, and gradient boosting machines demonstrated durability and precision in the face of adversarial attacks, showcasing the strength of unity.

Blockchain based Banking System Using Ethereum

This paper proposes a novel blockchain-based advanced banking system that leverages the distributed ledger technology of Ethereum to create a secure, transparent, and efficient financial system. The system utilizes a permission blockchain network, where participants are pre-authorized to join and contribute to the network. This ensures the security and integrity of the system, while still allowing for a wider range of participants than a fully public blockchain network. The system works by first having a user initiate a transaction request. The system then verifies the user's identity and ensures the authenticity of the request. The transaction is entered into the blockchain ledger after it has been validated. This ensures that the transaction is immutable and transparent, as all participants in the network can view the transaction details. The system also includes a fraud detection mechanism that can detect any changes made to the transaction after it has been recorded on the blockchain. This helps to ensure the security of the system and protect users from fraudulent activity. The proposed system has the potential to revolutionize the banking industry by providing a more secure, transparent, and efficient way to conduct financial transactions. Keywords: blockchain, online banking, ethereum, ganache, hash, smart contract, blocks

Fraud detection and prevention by face recognition with and without mask for banking application

Fraud detection and prevention by face recognition with and without mask for banking application

Research on the Application of Artificial Intelligence and Big Data Technology in Financial Fraud Detection

Financial fraud is a hidden criminal activity that has a serious impact on the stability of financial markets and investor confidence. Traditional fraud detection methods are often inefficient and unable to meet the rapidly changing fraudulent means. The development of artificial intelligence and big data technology has provided new solutions for financial fraud detection. This article aims to explore the current application status and methods of artificial intelligence and big data technology in financial fraud detection, and analyze the challenges and future development directions.

Comparative study of deep learning explainability and causal ai for fraud detection

Abstract This study aims to compare deep learning explainability (DLE) with explainable artificial intelligence and causal artificial intelligence (Causal AI) for fraud detection, emphasizing their distinct methodologies and potential to address critical challenges, particularly in finance. An empirical evaluation was conducted using the Bank Account Fraud datasets from NeurIPS 2022. DLE models, including deep learning architectures enhanced with interpretability techniques, were compared against Causal AI models that elucidate causal relationships in the data. DLE models demonstrated high accuracy (95% for Model A and 96% for Model B) and precision (97% for Model A and 95% for Model B) but exhibited reduced recall (98% for Model A and 97% for Model B) due to opaque decision-making processes. By contrast, Causal AI models showed balanced but lower performance with accuracy, precision, and recall, all at 60%. These findings underscore the need for transparent and reliable fraud detection systems, highlighting the trade-offs between model performance and interpretability. This study addresses a significant research gap by providing a comparative analysis of DLE and Causal AI in the context of fraud detection. The insights gained offer practical recommendations for enhancing model interpretability and reliability, contributing to advancements in AI-driven fraud detection systems in the financial sector.

Fraud Feature Boosting Mechanism and Spiral Oversampling Balancing Technique for Credit Card Fraud Detection

With the flourishing of the credit card business and Internet technology, the risk of fraudulent credit card transactions is ever-increasing due to the complex information involved in the credit card business. Since the high redundancy of feature information and imbalance of class distribution in transaction data, the performance of the existing machine learning-based models for detecting credit card fraudulent transactions still needs to be improved. Therefore, it is crucial to build fraud detection models for effective feature engineering and sampling techniques. This article proposes a credit card fraud detection model incorporating a fraud feature-boosting mechanism with a spiral oversampling balancing technique (SOBT). Specifically, we present a compound grouping elimination strategy to exclude highly redundant and correlated features from the credit card transaction dataset and improve the data quality. Furthermore, we design a multifactor synchronous embedding mechanism, which combines the performance evaluation metrics of the embedding model for each feature and improves the decision-making ability of each feature for the target domain. Moreover, we propose an SOBT to balance the ratio of legitimate to fraudulent transactions, which improves the ability of the fraud detection model to distinguish legitimate from fraudulent transactions. Extensive experimental results based on two real-world datasets demonstrate that our methods can facilitate efficient credit card fraud detection and achieve better performance than state-of-the-art methods.

A Privacy-Aware and Incremental Defense Method Against GAN-Based Poisoning Attack

Federated learning is usually utilized as a fraud detection framework in the domain of financial risk management, which promotes the model accuracy without training data exchange. One of the challenges in federated learning is the GAN-based poisoning attack. The GAN-based poisoning attack is a type of intractable poisoning attack that causes global model accuracy degradation and privacy leak. Most of the existing defenses for GAN-based poisoning attack have the three problems: 1) dependence on validation datasets; 2) incompetence of dealing with incremental poisoning attack; and 3) privacy leak. To address the above problems, we present a privacy-aware and incremental defense (PID) method to detect malicious participants and protect privacy. In PID, we design a method to accumulate the offset of model parameters from participants in all current epochs to represent the moving tendency for model parameters. Thus, we can distinguish the adversaries from normal participants based on the accumulations in this incremental poisoning attack. We also use multiple trust domains to reduce the rate of misjudging benign participants as adversaries. Moreover, a differentiated differential privacy is utilized before the global model sending to protect the privacy of participants’ training datasets in PID. The experiments conducted on two real-world datasets under financial fraud detection scenario demonstrate that the PID reduces the fallout of adversaries detection (the rate of misjudging benign participants as adversaries) by at least 51.1% and improve the speed of detecting all malicious participants by at least 33.4% compared with two popular defense methods. Besides, the privacy preserving of PID is also effective.

A Proposed Frame work for External Auditor using of Root Cause Analysis in Fraud Detection and Analysis

A Proposed Frame work for External Auditor using of Root Cause Analysis in Fraud Detection and Analysis

Leveraging Adversarial Augmentation on Imbalance Data for Online Trading Fraud Detection

Nowadays, the emergence of online trading greatly facilitates people’s life. Meanwhile, online trading also brings hidden dangers, such as online fraudulent trading. To solve the issue, researchers have proposed many different detection models. However, in actual business scenarios, fraudulent transactions usually only account for a small portion of normal transactions, resulting in extremely imbalanced data. Besides, the concealment of fraud is reflected in that the fraudsters are imitating the normal transactions of users, posing a huge challenge for fraudulent transaction detection modeling. Inspired by generative adversarial networks (GANs), we propose a GAN-based framework to detect online banking fraud on extremely imbalanced data, called BalanceGAN. A fraud detection model is first pretrained using the data generated by the generator and then the model is fine-tuned using transfer learning on real-world datasets, by using this approach to address data imbalances. Compared with the conventional methods for solving imbalanced data, our BalanceGAN can avoid over-fitting of the model relatively, experiments on two real datasets show that our BalanceGAN has more than 10% performance improvement in Precision and Recall.

The Transformative Impact of AI in Finance and Banking

The transformative impact of artificial intelligence (AI) in finance and banking is pro7 found, revolutionizing the way financial institutions operate, interact with customers, and make 8 decisions. This article explores the technological landscape that has paved the way for AI adoption, including falling data storage costs, data availability, advancements in machine learning, cost reduction, regulatory compliance, competitive advantage, risk management, customer experience, fraud detection, increased connectivity, and rapid advances in AI technologies. It discusses how AI is enhancing customer support, improving security through fraud detection algorithms, and enhancing credit scoring accuracy through machine learning. The value creation potential of AI in banking includes unlocking up to $1 trillion of incremental value annually through personalized services, cost reduction via automation, and uncovering new opportunities. Additionally, it provides examples of AI applications in banking, including personalization, automation, and insight extraction, showcasing how AI is transforming the industry. Despite these advancements, the article acknowledges challenges such as a lack of clear strategy, legacy systems, and fragmented data assets and proposes solutions like promoting a growth mindset and responsible AI deployment. It also addresses current issues in the banking sector, such as cyberattacks, voice cloning, and fraud, emphasizing the importance of AI in addressing these challenges. Overall, the article highlights the transformative potential of AI in finance and banking, urging banks to embrace an AI-first mindset for sustained growth and innovation.

Social care data and its fitness for integrated health and social care service governance: an exploratory qualitative analysis in the Dutch context

IntroductionTo date, little is known on how social care data could be used to inform performance-based governance to accelerate progress towards integrated health and social care.Objectives and designThis study aims...