ABSTRACT
When occupational fraud is detected, the organization—the victim in the fraud case—decides whether or not to terminate and/or refer the case to law enforcement for possible prosecution. We ...use survey data collected by the Association of Certified Fraud Examiners (ACFE) to examine the impact of fraud duration, organization type, and perpetrator status on a victim organization’s decision to pursue a particular punishment outcome against the principal perpetrator. We find that fraud duration is an important attribute in determining whether and how victim organizations pursue punishments. Furthermore, fraud duration interacts with victim organization type and with perpetrator status to influence the punishment outcome selected by the victim organization. Our study contributes to the fraud literature by considering the interactions between perpetrator and victim organization characteristics on punishment outcomes and has practical implications for victim organizations and the certified fraud examiners who advise them.
Data Availability: Data are available from the Association of Certified Fraud Examiners (ACFE).
JEL Classifications: M40; M41; M49; L32; L33.
This article addresses the pervasive issue of fraud in financial transactions by introducing the Graph Attention Network (GAN) into graph neural networks. The article integrates Node Attention ...Networks and Semantic Attention Networks to construct a Dual-Head Attention Network module, enabling a comprehensive analysis of complex relationships in user transaction data. This approach adeptly handles non-linear features and intricate data interaction relationships. The article incorporates a Gradient-Boosting Decision Tree (GBDT) to enhance fraud identification to create the GBDT–Dual-channel Graph Attention Network (GBDT-DGAN). In a bid to ensure user privacy, this article introduces blockchain technology, culminating in the development of a financial anti-fraud model that fuses blockchain with the GBDT-DGAN algorithm. Experimental verification demonstrates the model’s accuracy, reaching 93.82%, a notable improvement of at least 5.76% compared to baseline algorithms such as Convolutional Neural Networks. The recall and F1 values stand at 89.5% and 81.66%, respectively. Additionally, the model exhibits superior network data transmission security, maintaining a packet loss rate below 7%. Consequently, the proposed model significantly outperforms traditional approaches in financial fraud detection accuracy and ensures excellent network data transmission security, offering an efficient and secure solution for fraud detection in the financial domain.
Purpose
This paper aims to present a bibliometric analysis of publications from the Scopus database on fraud detection studies.
Design/methodology/approach
The current research used Microsoft Excel ...to conduct the frequency analysis, VOSviewer for data visualisation and Harzing’s Publish or Perish for citation metrics and analysis.
Findings
In alignment with these research results, the publications on fraud detection studies have been consistently increasing since 2005. India was rated first as the most active country in fraud detection research. Tongji University from China was the most active institution that published significant publications related to fraud detection research. A total of 160 scholars from 89 various countries and 160 different institutions published several fraud detections studies with multi-authors’ participation in different languages.
Originality/value
To the best of the authors knowledge, this study is the first study to review fraud detections publications in the Scopus science database.
In the last decade, the ease of online payment has opened up many new opportunities for e-commerce, lowering the geographical boundaries for retail. While e-commerce is still gaining popularity, it ...is also the playground of fraudsters who try to misuse the transparency of online purchases and the transfer of credit card records. This paper proposes APATE, a novel approach to detect fraudulent credit card transactions conducted in online stores. Our approach combines (1) intrinsic features derived from the characteristics of incoming transactions and the customer spending history using the fundamentals of RFM (Recency–Frequency–Monetary); and (2) network-based features by exploiting the network of credit card holders and merchants and deriving a time-dependent suspiciousness score for each network object. Our results show that both intrinsic and network-based features are two strongly intertwined sides of the same picture. The combination of these two types of features leads to the best performing models which reach AUC-scores higher than 0.98.
•We develop a fraud detection system for credit card transactions combining RFM variables and Social Network Analysis.•The system profiles both the purchasing behavior of the credit card holder and the dynamics between merchants and customers.•Results show AUC values of 0.98 in the best case: RFM and Social Network-related variables in a Random Forest model.
We study the impact of network information for social security fraud detection. In a social security system, companies have to pay taxes to the government. This study aims to identify those companies ...that intentionally go bankrupt to avoid contributing their taxes. We link companies to each other through their shared resources, because some resources are the instigators of fraud. We introduce GOTCHA!, a new approach to define and extract features from a time-weighted network and to exploit and integrate network-based and intrinsic features in fraud detection. The GOTCHA! propagation algorithm diffuses fraud through the network, labeling the unknown and anticipating future fraud while simultaneously decaying the importance of past fraud. We find that domain-driven network variables have a significant impact on detecting past and future frauds and improve the baseline by detecting up to 55% additional fraudsters over time.
This paper was accepted by Lorin Hitt, information systems
.
Purpose
According to the Association of Certified Fraud Examiners, financial statement fraud represents the smallest amount of fraud cases but results in the greatest monetary loss. The researcher ...previously investigated the characteristics of financial statement fraud and determined the presence of 16 fraud indicators. The purpose of this study is to establish whether investors and other stakeholders can detect and identify financial statement fraud using these characteristics in an analysis of a company’s annual report.
Design/methodology/approach
This study analyses a financial statement fraud case, using the same techniques that were previously applied, including horizontal, vertical and ratio analysis. These are preferred because stakeholders have relatively easy access to them.
Findings
The findings show several fraud characteristics, with a few additional ones not previously found prevalent. Financial statement fraud thus tends to differ between cases. It is also easier to detect and identify fraud indicators ex post facto.
Originality/value
This study is a practical case showing that financial statement fraud can be detected and identified in the financial statements of companies that commit fraud.
Fraud, especially in the academic field was a challenge in every educational institution. Every fraud has the motives behind it. One of the framework that explain the motives of fraud is fraud ...hexagon. Therefore, this research use fraud hexagon framework as a tool and concept for detecting academic fraud. This research was conducted at the Faculty of Economics and Business, Satya Wacana Christian University with a total sample of 270 active accounting students who were obtained using the Slovin formula. This research aim to examine the variables in the fraud hexagon as a student’s motive to intend to commit academic fraud. For the research method, this study use quantitative approach with six independent variables and one dependent variable. Based on the result of research that obtained, simultaneously, the six factors influence the intention to commit academic fraud at the Faculty of Economics and Business, Satya Wacana Christian University. While partially, the factors that have a significant effect to commit academic fraud is rationalization.
This paper describes the empirical universe of financial fraud as it has been documented in the academic literature. Specifically, it describes the different forms of fraudulent behaviour in the ...context of financial market activities, the prevalence and consequences of such behaviour as identified by previous research, and the economic and market structures that scholars believe facilitate it. To structure the discussion, a conceptual distinction is made between three types of financial fraud: false financial disclosures, financial scams, and financial mis‐selling. The findings of the literature review highlight a number of recent developments that scholars think have facilitated the occurrence of financial fraud, including (1) the development of new fundamental conflicts of interest and perverse incentive structures in the financial industry; (2) an influx of unsophisticated, gullible participants in the financial marketplace; (3) the increasing complexity involved in financial market transactions as a result of rapid technological, legal, and financial innovation and an ever‐widening menu of financial products; (4) an increase in the use of justified secrecy in the form of a mystification of trading models adopted by fund managers.