This paper proposes a novel hybrid fraud detection framework that integrates multi-stage feature selection,unsupervised clustering,and ensemble learning to improve classification performance in financial transaction m...This paper proposes a novel hybrid fraud detection framework that integrates multi-stage feature selection,unsupervised clustering,and ensemble learning to improve classification performance in financial transaction monitoring systems.The framework is structured into three core layers:(1)feature selection using Recursive Feature Elimination(RFE),Principal Component Analysis(PCA),and Mutual Information(MI)to reduce dimensionality and enhance input relevance;(2)anomaly detection through unsupervised clustering using K-Means,Density-Based Spatial Clustering(DBSCAN),and Hierarchical Clustering to flag suspicious patterns in unlabeled data;and(3)final classification using a voting-based hybrid ensemble of Support Vector Machine(SVM),Random Forest(RF),and Gradient Boosting Classifier(GBC).The experimental evaluation is conducted on a synthetically generated dataset comprising one million financial transactions,with 5% labelled as fraudulent,simulating realistic fraud rates and behavioural features,including transaction time,origin,amount,and geo-location.The proposed model demonstrated a significant improvement over baseline classifiers,achieving an accuracy of 99%,a precision of 99%,a recall of 97%,and an F1-score of 99%.Compared to individual models,it yielded a 9% gain in overall detection accuracy.It reduced the false positive rate to below 3.5%,thereby minimising the operational costs associated with manually reviewing false alerts.The model’s interpretability is enhanced by the integration of Shapley Additive Explanations(SHAP)values for feature importance,supporting transparency and regulatory auditability.These results affirm the practical relevance of the proposed system for deployment in real-time fraud detection scenarios such as credit card transactions,mobile banking,and cross-border payments.The study also highlights future directions,including the deployment of lightweight models and the integration of multimodal data for scalable fraud analytics.展开更多
With the increased accessibility of global trade information,transaction fraud has become a major worry in global banking and commerce security.The incidence and magnitude of transaction fraud are increasing daily,res...With the increased accessibility of global trade information,transaction fraud has become a major worry in global banking and commerce security.The incidence and magnitude of transaction fraud are increasing daily,resulting in significant financial losses for both customers and financial professionals.With improvements in data mining and machine learning in computer science,the capacity to detect transaction fraud is becoming increasingly attainable.The primary goal of this research is to undertake a comparative examination of cutting-edge machine-learning algorithms developed to detect credit card fraud.The research looks at the efficacy of these machine learning algorithms using a publicly available dataset of credit card transactions performed by European cardholders in 2023,comprising around 550,000 records.The study uses this dataset to assess the performance of well-established machine learning models,measuring their accuracy,recall,and F1 score.In addition,the study includes a confusion matrix for all models to aid in evaluation and training time duration.Machin learning models,including Logistic regression,random forest,extra trees,and LGBM,achieve high accuracy and precision in the credit card fraud detection dataset,with a reported accuracy,recall,and F1 score of 1.00 for both classes.展开更多
Fraud of credit cards is a major issue for financial organizations and individuals.As fraudulent actions become more complex,a demand for better fraud detection systems is rising.Deep learning approaches have shown pr...Fraud of credit cards is a major issue for financial organizations and individuals.As fraudulent actions become more complex,a demand for better fraud detection systems is rising.Deep learning approaches have shown promise in several fields,including detecting credit card fraud.However,the efficacy of these models is heavily dependent on the careful selection of appropriate hyperparameters.This paper introduces models that integrate deep learning models with hyperparameter tuning techniques to learn the patterns and relationships within credit card transaction data,thereby improving fraud detection.Three deep learning models:AutoEncoder(AE),Convolution Neural Network(CNN),and Long Short-Term Memory(LSTM)are proposed to investigate how hyperparameter adjustment impacts the efficacy of deep learning models used to identify credit card fraud.The experiments conducted on a European credit card fraud dataset using different hyperparameters and three deep learning models demonstrate that the proposed models achieve a tradeoff between detection rate and precision,leading these models to be effective in accurately predicting credit card fraud.The results demonstrate that LSTM significantly outperformed AE and CNN in terms of accuracy(99.2%),detection rate(93.3%),and area under the curve(96.3%).These proposed models have surpassed those of existing studies and are expected to make a significant contribution to the field of credit card fraud detection.展开更多
A dandelion algorithm(DA) is a recently developed intelligent optimization algorithm for function optimization problems. Many of its parameters need to be set by experience in DA,which might not be appropriate for all...A dandelion algorithm(DA) is a recently developed intelligent optimization algorithm for function optimization problems. Many of its parameters need to be set by experience in DA,which might not be appropriate for all optimization problems. A self-adapting and efficient dandelion algorithm is proposed in this work to lower the number of DA's parameters and simplify DA's structure. Only the normal sowing operator is retained;while the other operators are discarded. An adaptive seeding radius strategy is designed for the core dandelion. The results show that the proposed algorithm achieves better performance on the standard test functions with less time consumption than its competitive peers. In addition, the proposed algorithm is applied to feature selection for credit card fraud detection(CCFD), and the results indicate that it can obtain higher classification and detection performance than the-state-of-the-art methods.展开更多
The aim of this study is to examine the qualities that auditors engaged in detecting potential fraud within multinational corporations in Sub-Saharan Africa should possess.To achieve this goal,a quantitative approach ...The aim of this study is to examine the qualities that auditors engaged in detecting potential fraud within multinational corporations in Sub-Saharan Africa should possess.To achieve this goal,a quantitative approach was used to develop and test a research model based on three theories:agency theory,attribution theory,and cognitive dissonance theory.Responses from a panel of two hundred and nine(209)auditors who conducted a legal audit mission in a Sub-Saharan multinational were analyzed using SmartPLS 3.3.3 software.The results emphasize the crucial importance of auditors’competence and continuous training in fraud detection.However,professional skepticism and time pressure were found to be non-significant in this context.This conclusion provides essential insights for auditors,highlighting the key qualities needed to effectively address fraud detection within multinational corporations in Sub-Saharan Africa.展开更多
Credit card fraud remains a significant challenge, with financial losses and consumer protection at stake. This study addresses the need for practical, real-time fraud detection methodologies. Using a Kaggle credit ca...Credit card fraud remains a significant challenge, with financial losses and consumer protection at stake. This study addresses the need for practical, real-time fraud detection methodologies. Using a Kaggle credit card dataset, I tackle class imbalance using the Synthetic Minority Oversampling Technique (SMOTE) to enhance modeling efficiency. I compare several machine learning algorithms, including Logistic Regression, Linear Discriminant Analysis, K-nearest Neighbors, Classification and Regression Tree, Naive Bayes, Support Vector, Random Forest, XGBoost, and Light Gradient-Boosting Machine to classify transactions as fraud or genuine. Rigorous evaluation metrics, such as AUC, PRAUC, F1, KS, Recall, and Precision, identify the Random Forest as the best performer in detecting fraudulent activities. The Random Forest model successfully identifies approximately 92% of transactions scoring 90 and above as fraudulent, equating to a detection rate of over 70% for all fraudulent transactions in the test dataset. Moreover, the model captures more than half of the fraud in each bin of the test dataset. SHAP values provide model explainability, with the SHAP summary plot highlighting the global importance of individual features, such as “V12” and “V14”. SHAP force plots offer local interpretability, revealing the impact of specific features on individual predictions. This study demonstrates the potential of machine learning, particularly the Random Forest model, for real-time credit card fraud detection, offering a promising approach to mitigate financial losses and protect consumers.展开更多
As financial criminal methods become increasingly sophisticated, traditional anti-money laundering and fraud detection approaches face significant challenges. This study focuses on the application technologies and cha...As financial criminal methods become increasingly sophisticated, traditional anti-money laundering and fraud detection approaches face significant challenges. This study focuses on the application technologies and challenges of big data analytics in anti-money laundering and financial fraud detection. The research begins by outlining the evolutionary trends of financial crimes and highlighting the new characteristics of the big data era. Subsequently, it systematically analyzes the application of big data analytics technologies in this field, including machine learning, network analysis, and real-time stream processing. Through case studies, the research demonstrates how these technologies enhance the accuracy and efficiency of anomalous transaction detection. However, the study also identifies challenges faced by big data analytics, such as data quality issues, algorithmic bias, and privacy protection concerns. To address these challenges, the research proposes solutions from both technological and managerial perspectives, including the application of privacy-preserving technologies like federated learning. Finally, the study discusses the development prospects of Regulatory Technology (RegTech), emphasizing the importance of synergy between technological innovation and regulatory policies. This research provides guidance for financial institutions and regulatory bodies in optimizing their anti-money laundering and fraud detection strategies.展开更多
Supply Chain Finance(SCF)is important for improving the effectiveness of supply chain capital operations and reducing the overall management cost of a supply chain.In recent years,with the deep integration of supply c...Supply Chain Finance(SCF)is important for improving the effectiveness of supply chain capital operations and reducing the overall management cost of a supply chain.In recent years,with the deep integration of supply chain and Internet,Big Data,Artificial Intelligence,Internet of Things,Blockchain,etc.,the efficiency of supply chain financial services can be greatly promoted through building more customized risk pricing models and conducting more rigorous investment decision-making processes.However,with the rapid development of new technologies,the SCF data has been massively increased and new financial fraud behaviors or patterns are becoming more covertly scattered among normal ones.The lack of enough capability to handle the big data volumes and mitigate the financial frauds may lead to huge losses in supply chains.In this article,a distributed approach of big data mining is proposed for financial fraud detection in a supply chain,which implements the distributed deep learning model of Convolutional Neural Network(CNN)on big data infrastructure of Apache Spark and Hadoop to speed up the processing of the large dataset in parallel and reduce the processing time significantly.By training and testing on the continually updated SCF dataset,the approach can intelligently and automatically classify the massive data samples and discover the fraudulent financing behaviors,so as to enhance the financial fraud detection with high precision and recall rates,and reduce the losses of frauds in a supply chain.展开更多
In recent years,the rapid development of e-commerce exposes great vulnerabilities in online transactions for fraudsters to exploit.Credit card transactions take a salient role in nowadays’online transactions for its ...In recent years,the rapid development of e-commerce exposes great vulnerabilities in online transactions for fraudsters to exploit.Credit card transactions take a salient role in nowadays’online transactions for its obvious advantages including discounts and earning credit card points.So credit card fraudulence has become a target of concern.In order to deal with the situation,credit card fraud detection based on machine learning is been studied recently.Yet,it is difficult to detect fraudulent transactions due to data imbalance(normal and fraudulent transactions),for which Smote algorithm is proposed in order to resolve data imbalance.The assessment of Light Gradient Boosting Machine model which proposed in the paper depends much on datasets collected from clients’daily transactions.Besides,to prove the new model’s superiority in detecting credit card fraudulence,Light Gradient Boosting Machine model is compared with Random Forest and Gradient Boosting Machine algorithm in the experiment.The results indicate that Light Gradient Boosting Machine model has a good performance.The experiment in credit card fraud detection based on Light Gradient Boosting Machine model achieved a total recall rate of 99%in real dataset and fast feedback,which proves the new model’s efficiency in detecting credit card fraudulence.展开更多
Credit Card Fraud Detection(CCFD)is an essential technology for banking institutions to control fraud risks and safeguard their reputation.Class imbalance and insufficient representation of feature data relating to cr...Credit Card Fraud Detection(CCFD)is an essential technology for banking institutions to control fraud risks and safeguard their reputation.Class imbalance and insufficient representation of feature data relating to credit card transactions are two prevalent issues in the current study field of CCFD,which significantly impact classification models’performance.To address these issues,this research proposes a novel CCFD model based on Multifeature Fusion and Generative Adversarial Networks(MFGAN).The MFGAN model consists of two modules:a multi-feature fusion module for integrating static and dynamic behavior data of cardholders into a unified highdimensional feature space,and a balance module based on the generative adversarial network to decrease the class imbalance ratio.The effectiveness of theMFGAN model is validated on two actual credit card datasets.The impacts of different class balance ratios on the performance of the four resamplingmodels are analyzed,and the contribution of the two different modules to the performance of the MFGAN model is investigated via ablation experiments.Experimental results demonstrate that the proposed model does better than state-of-the-art models in terms of recall,F1,and Area Under the Curve(AUC)metrics,which means that the MFGAN model can help banks find more fraudulent transactions and reduce fraud losses.展开更多
Background:The reputation system has been designed as an effective mechanism to reduce risks associated with online shopping for customers.However,it is vulnerable to rating fraud.Some raters may inject unfairly high ...Background:The reputation system has been designed as an effective mechanism to reduce risks associated with online shopping for customers.However,it is vulnerable to rating fraud.Some raters may inject unfairly high or low ratings to the system so as to promote their own products or demote their competitors.Method:This study explores the rating fraud by differentiating the subjective fraud from objective fraud.Then it discusses the effectiveness of blockchain technology in objective fraud and its limitation in subjective fraud,especially the rating fraud.Lastly,it systematically analyzes the robustness of blockchain-based reputation systems in each type of rating fraud.Results:The detection of fraudulent raters is not easy since they can behave strategically to camouflage themselves.We explore the potential strengths and limitations of blockchain-based reputation systems under two attack goals:ballot-stuffing and bad-mouthing,and various attack models including constant attack,camouflage attack,whitewashing attack and sybil attack.Blockchain-based reputation systems are more robust against bad-mouthing than ballot-stuffing fraud.Conclusions:Blockchain technology provides new opportunities for redesigning the reputation system.Blockchain systems are very effective in preventing objective information fraud,such as loan application fraud,where fraudulent information is fact-based.However,their effectiveness is limited in subjective information fraud,such as rating fraud,where the ground-truth is not easily validated.Blockchain systems are effective in preventing bad mouthing and whitewashing attack,but they are limited in detecting ballot-stuffing under sybil attack,constant attacks and camouflage attack.展开更多
This work is concerned with GSM subscription fraud detection system using some network techniques. Fraud is a hitch around the globe with huge loss of income. Fraud has an effect on the credibility and performance of ...This work is concerned with GSM subscription fraud detection system using some network techniques. Fraud is a hitch around the globe with huge loss of income. Fraud has an effect on the credibility and performance of telecommunication companies. The most difficult problem that faces the industry is the fact that fraud is dynamic, which means that whenever fraudsters feel that they will be detected, they devise other ways to circumvent security measures. In such cases, the perpetrators’ intention is to completely avoid or at least reduce the charges for using the services. Subscription fraud is one of the major types of telecommunication fraud in which a customer obtains an account without intention to pay the bill. Thus at the level of a phone number, all transactions from the number will be fraudulent. In such cases abnormal usage occurs throughout the active period of the account;which is usually used for call selling or intensive self usage. This provides a means for illegal high profit business for fraudsters requiring minimal investment and relatively low risk of getting caught. A system to prevent subscription fraud in GSM telecommunications with high impact on long distance carriers is proposed to detect fraud. The system employs adaptive flexible techniques using advanced data analysis like Artificial Neural Networks (ANN). This study aims at developing a fraud detection model occurrence in GSM Network. The paper also gives analysis of the fraud detection Systems, fraud detection and prevention, fraud prevention methods etc. Fraud affects us all and is of particular concern to those who manage large government and business organisations where the potential losses are greatest. The operation of a mobile network is complex, and fraudsters invest a lot of energy to find and exploit every weakness of the system. A typical example would be subscription fraud, where a fraudster acquires a subscription to the mobile network under a false identity;and start reselling the use of his phone to unscrupulous customers (typically for international calls to distant foreign countries) at rate less than the regular tariff.展开更多
With the rise of internet facilities,a greater number of people have started doing online transactions at an exponential rate in recent years as the online transaction system has eliminated the need of going to the ba...With the rise of internet facilities,a greater number of people have started doing online transactions at an exponential rate in recent years as the online transaction system has eliminated the need of going to the bank physically for every transaction.However,the fraud cases have also increased causing the loss of money to the consumers.Hence,an effective fraud detection system is the need of the hour which can detect fraudulent transactions automatically in real-time.Generally,the genuine transactions are large in number than the fraudulent transactions which leads to the class imbalance problem.In this research work,an online transaction fraud detection system using deep learning has been proposed which can handle class imbalance problem by applying algorithm-level methods which modify the learning of the model to focus more on the minority class i.e.,fraud transactions.A novel loss function named Weighted Hard-Reduced Focal Loss(WH-RFL)has been proposed which has achieved maximum fraud detection rate i.e.,True PositiveRate(TPR)at the cost of misclassification of few genuine transactions as high TPR is preferred over a high True Negative Rate(TNR)in fraud detection system and same has been demonstrated using three publicly available imbalanced transactional datasets.Also,Thresholding has been applied to optimize the decision threshold using cross-validation to detect maximum number of frauds and it has been demonstrated by the experimental results that the selection of the right thresholding method with deep learning yields better results.展开更多
With the fast development of Internet technology,more and more payments are fulfilled by mobile Apps in an electrical way which significantly saves time and efforts for payment.Such a change has benefited a large numb...With the fast development of Internet technology,more and more payments are fulfilled by mobile Apps in an electrical way which significantly saves time and efforts for payment.Such a change has benefited a large number of individual users as well as merchants,and a few major players for payment service have emerged in China.As a result,the payment service competition becomes even fierce,and various promotion activities have been launched for attracting more users by the payment service providers.In this paper,the problem focused on is fraud payment detection,which in fact has been a major concern for the providers who spend a significant amount of money to popularize their payment tools.This paper tries the graph computing-based visualization to the behavior of transactions occuring between the individual users and merchants.Specifically,a network analysisbased pipeline has been built.It consists of the following key components:transaction network building based on daily records aggregation;transaction network filtering based on edge and node removal;transaction network decomposition by community detection;detected transaction community visualization.The proposed approach is verified on the real-world dataset collected from the major player in the payment market in Asia and the qualitative results show the efficiency of the method.展开更多
Telecommunication fraud has run rampant recently worldwide.However,previous studies depend highly on expert knowledge-based feature engineering to extract behavior information,which cannot adapt to the fastchanging mo...Telecommunication fraud has run rampant recently worldwide.However,previous studies depend highly on expert knowledge-based feature engineering to extract behavior information,which cannot adapt to the fastchanging modes of fraudulent subscribers.Therefore,we propose a new taxonomy that needs no hand-designed features but directly takes raw Call DetailRecords(CDR)data as input for the classifier.Concretely,we proposed a fraud detectionmethod using a convolutional neural network(CNN)by taking CDR data as images and applying computer vision techniques like image augmentation.Comprehensive experiments on the real-world dataset from the 2020 Digital Sichuan Innovation Competition show that our proposed method outperforms the classic methods in many metrics with excellent stability in both the changes of quantity and the balance of samples.Compared with the state-of-the-art method,the proposed method has achieved about 89.98%F1-score and 92.93%AUC,improving 2.97%and 0.48%,respectively.With the augmentation technique,the model’s performance can be further enhanced by a 91.09%F1-score and a 94.49%AUC respectively.Beyond telecommunication fraud detection,our method can also be extended to other text datasets to automatically discover new features in the view of computer vision and its powerful methods.展开更多
Auditing standards require external auditors to provide reasonable assurance that the financial statements are free from material misstatements, either due to fraud or error. Inability of the external auditors to dete...Auditing standards require external auditors to provide reasonable assurance that the financial statements are free from material misstatements, either due to fraud or error. Inability of the external auditors to detect the material misstatements, particularly fraud, may expose them to litigation. The present study aims to examine the effect of personality factors （i.e., neuroticism, extraversion, conscientiousness, openness to experience and agreeableness） on the external auditors＇ ability to detect the likelihood of fraud. An experimental approach is adopted by sending case materials to audit partners and audit managers attached to auditing firms operating in Malaysia. The result shows that personality does not have a positive effect on the external auditors＇ ability to detect the likelihood of fraud.展开更多
The rapid growth of technology impacts all aspects of modern life, including banking and financial transactions. While these industries benefit significantly from technological advancements, they also face challenges ...The rapid growth of technology impacts all aspects of modern life, including banking and financial transactions. While these industries benefit significantly from technological advancements, they also face challenges such as credit card fraud, the most prevalent type of financial fraud. Each year, such fraud leads to billions of dollars in losses for banks, financial institutions, and customers. Although many machine learning (ML) and, more recently, deep learning (DL) solutions have been developed to address this issue, most fail to strike an effective balance between speed and performance. Moreover, the reluctance of financial institutions to disclose their fraud datasets due to reputational risks adds further challenges. This study proposes a predictive model for credit card fraud detection that leverages the unique strengths of Energy-based Restricted Boltzmann Machines (EB-RBM) and Extended Long Short-Term Memory (xLSTM) models. EB-RBM is utilized for its ability to detect new and previously unseen fraudulent patterns, while xLSTM focuses on identifying known fraud types. These models are integrated using an ensemble approach to combine their strengths, achieving a balanced and reliable prediction system. The ensemble employs a bootstrap max-voting mechanism, assigning equal voting rights to EB-RBM and xLSTM, followed by result normalization and aggregation to classify transactions as fraudulent or genuine. The model’s performance is evaluated using metrics such as AUC-ROC, AUC-PR, precision, recall, F1-score, confusion matrix, and elapsed time. Experimental results on a real-world European cardholder dataset demonstrate that the proposed approach effectively balances speed and performance, outperforming recent models in the field.展开更多
The landscape of financial transactions has grown increasingly complex due to the expansion of global economic integration and advancements in information technology.This complexity poses greater challenges in detecti...The landscape of financial transactions has grown increasingly complex due to the expansion of global economic integration and advancements in information technology.This complexity poses greater challenges in detecting and managing financial fraud.This review explores the role of Graph Neural Networks(GNNs)in addressing these challenges by proposing a unified framework that categorizes existing GNN methodologies applied to financial fraud detection.Specifically,by examining a series of detailed research questions,this review delves into the suitability of GNNs for financial fraud detection,their deployment in real-world scenarios,and the design considerations that enhance their effectiveness.This review reveals that GNNs are exceptionally adept at capturing complex relational patterns and dynamics within financial networks,significantly outperforming traditional fraud detection methods.Unlike previous surveys that often overlook the specific potentials of GNNs or address them only superficially,our review provides a comprehensive,structured analysis,distinctly focusing on the multifaceted applications and deployments of GNNs in financial fraud detection.This review not only highlights the potential of GNNs to improve fraud detection mechanisms but also identifies current gaps and outlines future research directions to enhance their deployment in financial systems.Through a structured review of over 100 studies,this review paper contributes to the understanding of GNN applications in financial fraud detection,offering insights into their adaptability and potential integration strategies.展开更多
The e-commerce industry’s rapid growth,accelerated by the COVID-19 pandemic,has led to an alarming increase in digital fraud and associated losses.To establish a healthy e-commerce ecosystem,robust cyber security and...The e-commerce industry’s rapid growth,accelerated by the COVID-19 pandemic,has led to an alarming increase in digital fraud and associated losses.To establish a healthy e-commerce ecosystem,robust cyber security and anti-fraud measures are crucial.However,research on fraud detection systems has struggled to keep pace due to limited real-world datasets.Advances in artificial intelligence,Machine Learning(ML),and cloud computing have revitalized research and applications in this domain.While ML and data mining techniques are popular in fraud detection,specific reviews focusing on their application in e-commerce platforms like eBay and Facebook are lacking depth.Existing reviews provide broad overviews but fail to grasp the intricacies of ML algorithms in the e-commerce context.To bridge this gap,our study conducts a systematic literature review using the Preferred Reporting Items for Systematic reviews and Meta-Analysis(PRISMA)methodology.We aim to explore the effectiveness of these techniques in fraud detection within digital marketplaces and the broader e-commerce landscape.Understanding the current state of the literature and emerging trends is crucial given the rising fraud incidents and associated costs.Through our investigation,we identify research opportunities and provide insights to industry stakeholders on key ML and data mining techniques for combating e-commerce fraud.Our paper examines the research on these techniques as published in the past decade.Employing the PRISMA approach,we conducted a content analysis of 101 publications,identifying research gaps,recent techniques,and highlighting the increasing utilization of artificial neural networks in fraud detection within the industry.展开更多
Dynamic graph fraud detection aims to distinguish fraudulent entities that deviate significantly from most benign entities within an ever-changing graph network.However,when dealing with different financial fraud scen...Dynamic graph fraud detection aims to distinguish fraudulent entities that deviate significantly from most benign entities within an ever-changing graph network.However,when dealing with different financial fraud scenarios,existing methods face challenges,resulting in difficulty in effectively ensuring financial security.In fraud scenarios,transaction data are generated in real time,in which a strong temporal relationship between multiple fraudulent transactions is observed.Traditional dynamic graph models struggle to effectively balance the temporal features of nodes and spatial structural features,failing to handle different types of nodes in the graph network.In this study,to extract the temporal and structural information,we proposed a dynamic heterogeneous transaction graph embedding(DyHDGE)network based on a dynamic heterogeneous transaction graph,considering both temporal and structural information while incorporating heterogeneous data.To separately extract temporal relationships between transactions and spatial structural relationships between nodes,we used a heterogeneous temporal graph representation learning module and a temporal graph structure information extraction module.Additionally,we designed two loss functions to optimize node feature representations.Extensive experiments demonstrated that the proposed DyHDGE significantly outperformed previous state-of-the-art methods on two simulated datasets of financial fraud scenarios.This capability contributes to enhancing security in financial consumption scenarios.展开更多
基金funded by the Deanship of Scientific Research,Vice Presidency for Graduate Studies and Scientific Research,King Faisal University,Saudi Arabia[Grant No.KFU241683].
文摘This paper proposes a novel hybrid fraud detection framework that integrates multi-stage feature selection,unsupervised clustering,and ensemble learning to improve classification performance in financial transaction monitoring systems.The framework is structured into three core layers:(1)feature selection using Recursive Feature Elimination(RFE),Principal Component Analysis(PCA),and Mutual Information(MI)to reduce dimensionality and enhance input relevance;(2)anomaly detection through unsupervised clustering using K-Means,Density-Based Spatial Clustering(DBSCAN),and Hierarchical Clustering to flag suspicious patterns in unlabeled data;and(3)final classification using a voting-based hybrid ensemble of Support Vector Machine(SVM),Random Forest(RF),and Gradient Boosting Classifier(GBC).The experimental evaluation is conducted on a synthetically generated dataset comprising one million financial transactions,with 5% labelled as fraudulent,simulating realistic fraud rates and behavioural features,including transaction time,origin,amount,and geo-location.The proposed model demonstrated a significant improvement over baseline classifiers,achieving an accuracy of 99%,a precision of 99%,a recall of 97%,and an F1-score of 99%.Compared to individual models,it yielded a 9% gain in overall detection accuracy.It reduced the false positive rate to below 3.5%,thereby minimising the operational costs associated with manually reviewing false alerts.The model’s interpretability is enhanced by the integration of Shapley Additive Explanations(SHAP)values for feature importance,supporting transparency and regulatory auditability.These results affirm the practical relevance of the proposed system for deployment in real-time fraud detection scenarios such as credit card transactions,mobile banking,and cross-border payments.The study also highlights future directions,including the deployment of lightweight models and the integration of multimodal data for scalable fraud analytics.
文摘With the increased accessibility of global trade information,transaction fraud has become a major worry in global banking and commerce security.The incidence and magnitude of transaction fraud are increasing daily,resulting in significant financial losses for both customers and financial professionals.With improvements in data mining and machine learning in computer science,the capacity to detect transaction fraud is becoming increasingly attainable.The primary goal of this research is to undertake a comparative examination of cutting-edge machine-learning algorithms developed to detect credit card fraud.The research looks at the efficacy of these machine learning algorithms using a publicly available dataset of credit card transactions performed by European cardholders in 2023,comprising around 550,000 records.The study uses this dataset to assess the performance of well-established machine learning models,measuring their accuracy,recall,and F1 score.In addition,the study includes a confusion matrix for all models to aid in evaluation and training time duration.Machin learning models,including Logistic regression,random forest,extra trees,and LGBM,achieve high accuracy and precision in the credit card fraud detection dataset,with a reported accuracy,recall,and F1 score of 1.00 for both classes.
文摘Fraud of credit cards is a major issue for financial organizations and individuals.As fraudulent actions become more complex,a demand for better fraud detection systems is rising.Deep learning approaches have shown promise in several fields,including detecting credit card fraud.However,the efficacy of these models is heavily dependent on the careful selection of appropriate hyperparameters.This paper introduces models that integrate deep learning models with hyperparameter tuning techniques to learn the patterns and relationships within credit card transaction data,thereby improving fraud detection.Three deep learning models:AutoEncoder(AE),Convolution Neural Network(CNN),and Long Short-Term Memory(LSTM)are proposed to investigate how hyperparameter adjustment impacts the efficacy of deep learning models used to identify credit card fraud.The experiments conducted on a European credit card fraud dataset using different hyperparameters and three deep learning models demonstrate that the proposed models achieve a tradeoff between detection rate and precision,leading these models to be effective in accurately predicting credit card fraud.The results demonstrate that LSTM significantly outperformed AE and CNN in terms of accuracy(99.2%),detection rate(93.3%),and area under the curve(96.3%).These proposed models have surpassed those of existing studies and are expected to make a significant contribution to the field of credit card fraud detection.
基金supported by the Institutional Fund Projects(IFPIP-1481-611-1443)the Key Projects of Natural Science Research in Anhui Higher Education Institutions(2022AH051909)+1 种基金the Provincial Quality Project of Colleges and Universities in Anhui Province(2022sdxx020,2022xqhz044)Bengbu University 2021 High-Level Scientific Research and Cultivation Project(2021pyxm04)。
文摘A dandelion algorithm(DA) is a recently developed intelligent optimization algorithm for function optimization problems. Many of its parameters need to be set by experience in DA,which might not be appropriate for all optimization problems. A self-adapting and efficient dandelion algorithm is proposed in this work to lower the number of DA's parameters and simplify DA's structure. Only the normal sowing operator is retained;while the other operators are discarded. An adaptive seeding radius strategy is designed for the core dandelion. The results show that the proposed algorithm achieves better performance on the standard test functions with less time consumption than its competitive peers. In addition, the proposed algorithm is applied to feature selection for credit card fraud detection(CCFD), and the results indicate that it can obtain higher classification and detection performance than the-state-of-the-art methods.
文摘The aim of this study is to examine the qualities that auditors engaged in detecting potential fraud within multinational corporations in Sub-Saharan Africa should possess.To achieve this goal,a quantitative approach was used to develop and test a research model based on three theories:agency theory,attribution theory,and cognitive dissonance theory.Responses from a panel of two hundred and nine(209)auditors who conducted a legal audit mission in a Sub-Saharan multinational were analyzed using SmartPLS 3.3.3 software.The results emphasize the crucial importance of auditors’competence and continuous training in fraud detection.However,professional skepticism and time pressure were found to be non-significant in this context.This conclusion provides essential insights for auditors,highlighting the key qualities needed to effectively address fraud detection within multinational corporations in Sub-Saharan Africa.
文摘Credit card fraud remains a significant challenge, with financial losses and consumer protection at stake. This study addresses the need for practical, real-time fraud detection methodologies. Using a Kaggle credit card dataset, I tackle class imbalance using the Synthetic Minority Oversampling Technique (SMOTE) to enhance modeling efficiency. I compare several machine learning algorithms, including Logistic Regression, Linear Discriminant Analysis, K-nearest Neighbors, Classification and Regression Tree, Naive Bayes, Support Vector, Random Forest, XGBoost, and Light Gradient-Boosting Machine to classify transactions as fraud or genuine. Rigorous evaluation metrics, such as AUC, PRAUC, F1, KS, Recall, and Precision, identify the Random Forest as the best performer in detecting fraudulent activities. The Random Forest model successfully identifies approximately 92% of transactions scoring 90 and above as fraudulent, equating to a detection rate of over 70% for all fraudulent transactions in the test dataset. Moreover, the model captures more than half of the fraud in each bin of the test dataset. SHAP values provide model explainability, with the SHAP summary plot highlighting the global importance of individual features, such as “V12” and “V14”. SHAP force plots offer local interpretability, revealing the impact of specific features on individual predictions. This study demonstrates the potential of machine learning, particularly the Random Forest model, for real-time credit card fraud detection, offering a promising approach to mitigate financial losses and protect consumers.
文摘As financial criminal methods become increasingly sophisticated, traditional anti-money laundering and fraud detection approaches face significant challenges. This study focuses on the application technologies and challenges of big data analytics in anti-money laundering and financial fraud detection. The research begins by outlining the evolutionary trends of financial crimes and highlighting the new characteristics of the big data era. Subsequently, it systematically analyzes the application of big data analytics technologies in this field, including machine learning, network analysis, and real-time stream processing. Through case studies, the research demonstrates how these technologies enhance the accuracy and efficiency of anomalous transaction detection. However, the study also identifies challenges faced by big data analytics, such as data quality issues, algorithmic bias, and privacy protection concerns. To address these challenges, the research proposes solutions from both technological and managerial perspectives, including the application of privacy-preserving technologies like federated learning. Finally, the study discusses the development prospects of Regulatory Technology (RegTech), emphasizing the importance of synergy between technological innovation and regulatory policies. This research provides guidance for financial institutions and regulatory bodies in optimizing their anti-money laundering and fraud detection strategies.
基金This research work is supported by Hunan Provincial Education Science 13th Five-Year Plan(Grant No.XJK016BXX001,Zhou,H.,http://jyt.hunan.gov.cn/jyt/sjyt/jky/index.html)Social Science Foundation of Hunan Province(Grant No.17YBA049,Zhou,H.,https://sk.rednet.cn/channel/7862.html)The work is also supported by Open Foundation for University Innovation Platform from Hunan Province,China(Grand No.18K103,Sun,G.,http://kxjsc.gov.hnedu.cn/).
文摘Supply Chain Finance(SCF)is important for improving the effectiveness of supply chain capital operations and reducing the overall management cost of a supply chain.In recent years,with the deep integration of supply chain and Internet,Big Data,Artificial Intelligence,Internet of Things,Blockchain,etc.,the efficiency of supply chain financial services can be greatly promoted through building more customized risk pricing models and conducting more rigorous investment decision-making processes.However,with the rapid development of new technologies,the SCF data has been massively increased and new financial fraud behaviors or patterns are becoming more covertly scattered among normal ones.The lack of enough capability to handle the big data volumes and mitigate the financial frauds may lead to huge losses in supply chains.In this article,a distributed approach of big data mining is proposed for financial fraud detection in a supply chain,which implements the distributed deep learning model of Convolutional Neural Network(CNN)on big data infrastructure of Apache Spark and Hadoop to speed up the processing of the large dataset in parallel and reduce the processing time significantly.By training and testing on the continually updated SCF dataset,the approach can intelligently and automatically classify the massive data samples and discover the fraudulent financing behaviors,so as to enhance the financial fraud detection with high precision and recall rates,and reduce the losses of frauds in a supply chain.
文摘In recent years,the rapid development of e-commerce exposes great vulnerabilities in online transactions for fraudsters to exploit.Credit card transactions take a salient role in nowadays’online transactions for its obvious advantages including discounts and earning credit card points.So credit card fraudulence has become a target of concern.In order to deal with the situation,credit card fraud detection based on machine learning is been studied recently.Yet,it is difficult to detect fraudulent transactions due to data imbalance(normal and fraudulent transactions),for which Smote algorithm is proposed in order to resolve data imbalance.The assessment of Light Gradient Boosting Machine model which proposed in the paper depends much on datasets collected from clients’daily transactions.Besides,to prove the new model’s superiority in detecting credit card fraudulence,Light Gradient Boosting Machine model is compared with Random Forest and Gradient Boosting Machine algorithm in the experiment.The results indicate that Light Gradient Boosting Machine model has a good performance.The experiment in credit card fraud detection based on Light Gradient Boosting Machine model achieved a total recall rate of 99%in real dataset and fast feedback,which proves the new model’s efficiency in detecting credit card fraudulence.
基金supported by the National Key R&D Program of China(Nos.2022YFB3104103,and 2019QY1406)the National Natural Science Foundation of China(Nos.61732022,61732004,61672020,and 62072131).
文摘Credit Card Fraud Detection(CCFD)is an essential technology for banking institutions to control fraud risks and safeguard their reputation.Class imbalance and insufficient representation of feature data relating to credit card transactions are two prevalent issues in the current study field of CCFD,which significantly impact classification models’performance.To address these issues,this research proposes a novel CCFD model based on Multifeature Fusion and Generative Adversarial Networks(MFGAN).The MFGAN model consists of two modules:a multi-feature fusion module for integrating static and dynamic behavior data of cardholders into a unified highdimensional feature space,and a balance module based on the generative adversarial network to decrease the class imbalance ratio.The effectiveness of theMFGAN model is validated on two actual credit card datasets.The impacts of different class balance ratios on the performance of the four resamplingmodels are analyzed,and the contribution of the two different modules to the performance of the MFGAN model is investigated via ablation experiments.Experimental results demonstrate that the proposed model does better than state-of-the-art models in terms of recall,F1,and Area Under the Curve(AUC)metrics,which means that the MFGAN model can help banks find more fraudulent transactions and reduce fraud losses.
文摘Background:The reputation system has been designed as an effective mechanism to reduce risks associated with online shopping for customers.However,it is vulnerable to rating fraud.Some raters may inject unfairly high or low ratings to the system so as to promote their own products or demote their competitors.Method:This study explores the rating fraud by differentiating the subjective fraud from objective fraud.Then it discusses the effectiveness of blockchain technology in objective fraud and its limitation in subjective fraud,especially the rating fraud.Lastly,it systematically analyzes the robustness of blockchain-based reputation systems in each type of rating fraud.Results:The detection of fraudulent raters is not easy since they can behave strategically to camouflage themselves.We explore the potential strengths and limitations of blockchain-based reputation systems under two attack goals:ballot-stuffing and bad-mouthing,and various attack models including constant attack,camouflage attack,whitewashing attack and sybil attack.Blockchain-based reputation systems are more robust against bad-mouthing than ballot-stuffing fraud.Conclusions:Blockchain technology provides new opportunities for redesigning the reputation system.Blockchain systems are very effective in preventing objective information fraud,such as loan application fraud,where fraudulent information is fact-based.However,their effectiveness is limited in subjective information fraud,such as rating fraud,where the ground-truth is not easily validated.Blockchain systems are effective in preventing bad mouthing and whitewashing attack,but they are limited in detecting ballot-stuffing under sybil attack,constant attacks and camouflage attack.
文摘This work is concerned with GSM subscription fraud detection system using some network techniques. Fraud is a hitch around the globe with huge loss of income. Fraud has an effect on the credibility and performance of telecommunication companies. The most difficult problem that faces the industry is the fact that fraud is dynamic, which means that whenever fraudsters feel that they will be detected, they devise other ways to circumvent security measures. In such cases, the perpetrators’ intention is to completely avoid or at least reduce the charges for using the services. Subscription fraud is one of the major types of telecommunication fraud in which a customer obtains an account without intention to pay the bill. Thus at the level of a phone number, all transactions from the number will be fraudulent. In such cases abnormal usage occurs throughout the active period of the account;which is usually used for call selling or intensive self usage. This provides a means for illegal high profit business for fraudsters requiring minimal investment and relatively low risk of getting caught. A system to prevent subscription fraud in GSM telecommunications with high impact on long distance carriers is proposed to detect fraud. The system employs adaptive flexible techniques using advanced data analysis like Artificial Neural Networks (ANN). This study aims at developing a fraud detection model occurrence in GSM Network. The paper also gives analysis of the fraud detection Systems, fraud detection and prevention, fraud prevention methods etc. Fraud affects us all and is of particular concern to those who manage large government and business organisations where the potential losses are greatest. The operation of a mobile network is complex, and fraudsters invest a lot of energy to find and exploit every weakness of the system. A typical example would be subscription fraud, where a fraudster acquires a subscription to the mobile network under a false identity;and start reselling the use of his phone to unscrupulous customers (typically for international calls to distant foreign countries) at rate less than the regular tariff.
基金This research was supported by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(P0012724,The Competency Development Program for Industry Specialist)and the Soonchunhyang University Research Fund.
文摘With the rise of internet facilities,a greater number of people have started doing online transactions at an exponential rate in recent years as the online transaction system has eliminated the need of going to the bank physically for every transaction.However,the fraud cases have also increased causing the loss of money to the consumers.Hence,an effective fraud detection system is the need of the hour which can detect fraudulent transactions automatically in real-time.Generally,the genuine transactions are large in number than the fraudulent transactions which leads to the class imbalance problem.In this research work,an online transaction fraud detection system using deep learning has been proposed which can handle class imbalance problem by applying algorithm-level methods which modify the learning of the model to focus more on the minority class i.e.,fraud transactions.A novel loss function named Weighted Hard-Reduced Focal Loss(WH-RFL)has been proposed which has achieved maximum fraud detection rate i.e.,True PositiveRate(TPR)at the cost of misclassification of few genuine transactions as high TPR is preferred over a high True Negative Rate(TNR)in fraud detection system and same has been demonstrated using three publicly available imbalanced transactional datasets.Also,Thresholding has been applied to optimize the decision threshold using cross-validation to detect maximum number of frauds and it has been demonstrated by the experimental results that the selection of the right thresholding method with deep learning yields better results.
基金Supported by the National Natural Science Foundation of China(No.61972250)National Key Research and Development Program of China(No.2018AAA0100700,2016YFB1001003)the Program of Shanghai Academic/Technology Research Leader(No.19XD1433700)。
文摘With the fast development of Internet technology,more and more payments are fulfilled by mobile Apps in an electrical way which significantly saves time and efforts for payment.Such a change has benefited a large number of individual users as well as merchants,and a few major players for payment service have emerged in China.As a result,the payment service competition becomes even fierce,and various promotion activities have been launched for attracting more users by the payment service providers.In this paper,the problem focused on is fraud payment detection,which in fact has been a major concern for the providers who spend a significant amount of money to popularize their payment tools.This paper tries the graph computing-based visualization to the behavior of transactions occuring between the individual users and merchants.Specifically,a network analysisbased pipeline has been built.It consists of the following key components:transaction network building based on daily records aggregation;transaction network filtering based on edge and node removal;transaction network decomposition by community detection;detected transaction community visualization.The proposed approach is verified on the real-world dataset collected from the major player in the payment market in Asia and the qualitative results show the efficiency of the method.
基金This research was funded by the Double Top-Class Innovation research project in Cyberspace Security Enforcement Technology of People’s Public Security University of China(No.2023SYL07).
文摘Telecommunication fraud has run rampant recently worldwide.However,previous studies depend highly on expert knowledge-based feature engineering to extract behavior information,which cannot adapt to the fastchanging modes of fraudulent subscribers.Therefore,we propose a new taxonomy that needs no hand-designed features but directly takes raw Call DetailRecords(CDR)data as input for the classifier.Concretely,we proposed a fraud detectionmethod using a convolutional neural network(CNN)by taking CDR data as images and applying computer vision techniques like image augmentation.Comprehensive experiments on the real-world dataset from the 2020 Digital Sichuan Innovation Competition show that our proposed method outperforms the classic methods in many metrics with excellent stability in both the changes of quantity and the balance of samples.Compared with the state-of-the-art method,the proposed method has achieved about 89.98%F1-score and 92.93%AUC,improving 2.97%and 0.48%,respectively.With the augmentation technique,the model’s performance can be further enhanced by a 91.09%F1-score and a 94.49%AUC respectively.Beyond telecommunication fraud detection,our method can also be extended to other text datasets to automatically discover new features in the view of computer vision and its powerful methods.
文摘Auditing standards require external auditors to provide reasonable assurance that the financial statements are free from material misstatements, either due to fraud or error. Inability of the external auditors to detect the material misstatements, particularly fraud, may expose them to litigation. The present study aims to examine the effect of personality factors （i.e., neuroticism, extraversion, conscientiousness, openness to experience and agreeableness） on the external auditors＇ ability to detect the likelihood of fraud. An experimental approach is adopted by sending case materials to audit partners and audit managers attached to auditing firms operating in Malaysia. The result shows that personality does not have a positive effect on the external auditors＇ ability to detect the likelihood of fraud.
文摘The rapid growth of technology impacts all aspects of modern life, including banking and financial transactions. While these industries benefit significantly from technological advancements, they also face challenges such as credit card fraud, the most prevalent type of financial fraud. Each year, such fraud leads to billions of dollars in losses for banks, financial institutions, and customers. Although many machine learning (ML) and, more recently, deep learning (DL) solutions have been developed to address this issue, most fail to strike an effective balance between speed and performance. Moreover, the reluctance of financial institutions to disclose their fraud datasets due to reputational risks adds further challenges. This study proposes a predictive model for credit card fraud detection that leverages the unique strengths of Energy-based Restricted Boltzmann Machines (EB-RBM) and Extended Long Short-Term Memory (xLSTM) models. EB-RBM is utilized for its ability to detect new and previously unseen fraudulent patterns, while xLSTM focuses on identifying known fraud types. These models are integrated using an ensemble approach to combine their strengths, achieving a balanced and reliable prediction system. The ensemble employs a bootstrap max-voting mechanism, assigning equal voting rights to EB-RBM and xLSTM, followed by result normalization and aggregation to classify transactions as fraudulent or genuine. The model’s performance is evaluated using metrics such as AUC-ROC, AUC-PR, precision, recall, F1-score, confusion matrix, and elapsed time. Experimental results on a real-world European cardholder dataset demonstrate that the proposed approach effectively balances speed and performance, outperforming recent models in the field.
基金supported by the National Key R&D Program of China(No.2022YFB4501704)the National Natural Science Foundation of China(Grant No.62102287)the Shanghai Science and Technology Innovation Action Plan Project(Nos.22YS1400600 and 22511100700).
文摘The landscape of financial transactions has grown increasingly complex due to the expansion of global economic integration and advancements in information technology.This complexity poses greater challenges in detecting and managing financial fraud.This review explores the role of Graph Neural Networks(GNNs)in addressing these challenges by proposing a unified framework that categorizes existing GNN methodologies applied to financial fraud detection.Specifically,by examining a series of detailed research questions,this review delves into the suitability of GNNs for financial fraud detection,their deployment in real-world scenarios,and the design considerations that enhance their effectiveness.This review reveals that GNNs are exceptionally adept at capturing complex relational patterns and dynamics within financial networks,significantly outperforming traditional fraud detection methods.Unlike previous surveys that often overlook the specific potentials of GNNs or address them only superficially,our review provides a comprehensive,structured analysis,distinctly focusing on the multifaceted applications and deployments of GNNs in financial fraud detection.This review not only highlights the potential of GNNs to improve fraud detection mechanisms but also identifies current gaps and outlines future research directions to enhance their deployment in financial systems.Through a structured review of over 100 studies,this review paper contributes to the understanding of GNN applications in financial fraud detection,offering insights into their adaptability and potential integration strategies.
文摘The e-commerce industry’s rapid growth,accelerated by the COVID-19 pandemic,has led to an alarming increase in digital fraud and associated losses.To establish a healthy e-commerce ecosystem,robust cyber security and anti-fraud measures are crucial.However,research on fraud detection systems has struggled to keep pace due to limited real-world datasets.Advances in artificial intelligence,Machine Learning(ML),and cloud computing have revitalized research and applications in this domain.While ML and data mining techniques are popular in fraud detection,specific reviews focusing on their application in e-commerce platforms like eBay and Facebook are lacking depth.Existing reviews provide broad overviews but fail to grasp the intricacies of ML algorithms in the e-commerce context.To bridge this gap,our study conducts a systematic literature review using the Preferred Reporting Items for Systematic reviews and Meta-Analysis(PRISMA)methodology.We aim to explore the effectiveness of these techniques in fraud detection within digital marketplaces and the broader e-commerce landscape.Understanding the current state of the literature and emerging trends is crucial given the rising fraud incidents and associated costs.Through our investigation,we identify research opportunities and provide insights to industry stakeholders on key ML and data mining techniques for combating e-commerce fraud.Our paper examines the research on these techniques as published in the past decade.Employing the PRISMA approach,we conducted a content analysis of 101 publications,identifying research gaps,recent techniques,and highlighting the increasing utilization of artificial neural networks in fraud detection within the industry.
基金supported in part by the National Key Research and Development Program of China(2021YFC3300602)the National Natural Science Foundation of China(grant no.72204155)the Natural Science Foundation of Shanghai(grant no.23ZR1423100).
文摘Dynamic graph fraud detection aims to distinguish fraudulent entities that deviate significantly from most benign entities within an ever-changing graph network.However,when dealing with different financial fraud scenarios,existing methods face challenges,resulting in difficulty in effectively ensuring financial security.In fraud scenarios,transaction data are generated in real time,in which a strong temporal relationship between multiple fraudulent transactions is observed.Traditional dynamic graph models struggle to effectively balance the temporal features of nodes and spatial structural features,failing to handle different types of nodes in the graph network.In this study,to extract the temporal and structural information,we proposed a dynamic heterogeneous transaction graph embedding(DyHDGE)network based on a dynamic heterogeneous transaction graph,considering both temporal and structural information while incorporating heterogeneous data.To separately extract temporal relationships between transactions and spatial structural relationships between nodes,we used a heterogeneous temporal graph representation learning module and a temporal graph structure information extraction module.Additionally,we designed two loss functions to optimize node feature representations.Extensive experiments demonstrated that the proposed DyHDGE significantly outperformed previous state-of-the-art methods on two simulated datasets of financial fraud scenarios.This capability contributes to enhancing security in financial consumption scenarios.
