Search results

Purpose: This chapter aims to examine machine learning (ML) models for predicting credit card fraud (CCF).

Need for the study: With the advance of technology, the world is increasingly relying on credit cards rather than cash in daily life. This creates a slew of new opportunities for fraudulent individuals to abuse these cards. As of December 2020, global card losses reached $28.65billion, up 2.9% from $27.85 billion in 2018, according to the Nilson 2019 research. To safeguard the safety of credit card users, the credit card issuer should include a service that protects customers from potential risks. CCF has become a severe threat as internet buying has grown. To this goal, various studies in the field of automatic and real-time fraud detection are required. Due to their advantageous properties, the most recent ones employ a variety of ML algorithms and techniques to construct a well-fitting model to detect fraudulent transactions. When it comes to recognising credit card risk is huge and high-dimensional data, feature selection (FS) is critical for improving classification accuracy and fraud detection.

Methodology/design/approach: The objectives of this chapter are to construct a new model for credit card fraud detection (CCFD) based on principal component analysis (PCA) for FS and using supervised ML techniques such as K-nearest neighbour (KNN), ridge classifier, gradient boosting, quadratic discriminant analysis, AdaBoost, and random forest for classification of fraudulent and legitimate transactions. When compared to earlier experiments, the suggested approach demonstrates a high capacity for detecting fraudulent transactions. To be more precise, our model’s resilience is constructed by integrating the power of PCA for determining the most useful predictive features. The experimental analysis was performed on German credit card and Taiwan credit card data sets.

Findings: The experimental findings revealed that the KNN achieved an accuracy of 96.29%, recall of 100%, and precision of 96.29%, which is the best performing model on the German data set. While the ridge classifier was the best performing model on Taiwan Credit data with an accuracy of 81.75%, recall of 34.89, and precision of 66.61%.

Practical implications: The poor performance of the models on the Taiwan data revealed that it is an imbalanced credit card data set. The comparison of our proposed models with state-of-the-art credit card ML models showed that our results were competitive.

Consumption taxes are an integral part of government revenue in countries around the world and are often subject to consumer evasion. The rapid rise of electronic commerce has exacerbated this problem as cross-border selling over the internet has enabled foreign businesses to sell and avoid collection and remittance of tax on their sales.

In this paper, we search for the solution to this problem through the analysis of three tax collection models: vendor, financial institution, and internet service provider (ISP). In addition, we examine administrative tools that enable more effective collection as well as inducements for taxpayers or collection agents to carry out their responsibility.

We conclude that the ISP collection model is not feasible at this time. On the other hand, we find that the vendor model, when supplemented with appropriate administrative tools and inducements, and the financial institution model, both represent viable options for policymakers to consider.

Purpose: The study aims to explore the wider acceptance of blockchain technology and growing faith in this technology among all business domains to mitigate the chances of fraud in various sectors.

Design/Methodology/Approach: The authors focus on studies conducted during 2015–2022 using keywords such as blockchain, fraud detection and financial domain for Systematic Literature Review (SLR). The SLR approach entails two databases, namely, Scopus and IEEE Xplore, to seek relevant articles covering the effectiveness of blockchain technology in controlling financial fraud.

Findings: The findings of the research explored different types of business domains using blockchains in detecting fraud. They examined their effectiveness in other sectors such as insurance, banks, online transactions, real estate, credit card usage, etc.

Practical Implications: The results of this research highlight (1) the real-life applications of blockchain technology to secure the gateway for online transactions; (2) people from diverse backgrounds with different business objectives can strongly rely on blockchains to prevent fraud.

Originality/Value: The SLR conducted in this study assists in the identification of future avenues with practical implications, making researchers aware of the work so far carried out for checking the effectiveness of blockchain; however, it does not ignore the possibility of zero to less effectiveness in some businesses which is yet to be explored.

In the early days of the COVID-19 pandemic, an area could only report its first positive cases if the infection had spread into the area and if the infection was subsequently detected. A standard probit model does not correctly account for these two distinct latent processes but assumes there is a single underlying process for an observed outcome. A similar issue confounds research on other binary outcomes such as corporate wrongdoing, acquisitions, hiring, and new venture establishments. The bivariate probit model enables empirical analysis of two distinct latent binary processes that jointly produce a single observed binary outcome. One common challenge of applying the bivariate probit model is that it may not converge, especially with smaller sample sizes. We use Monte Carlo simulations to give guidance on the sample characteristics needed to accurately estimate a bivariate probit model. We then demonstrate the use of the bivariate probit to model infection and detection as two distinct processes behind county-level COVID-19 reports in the United States. Finally, we discuss several organizational outcomes that strategy scholars might analyze using the bivariate probit model in future research.

Over the past two years, fraudulent financial reporting has become a major concern of both the Securities and Exchange Commission and investors. These concerns have been spurred by evidence that several high-profile companies such as Enron, Tyco, WorldCom, and HealthSouth have published false and/or misleading financial reports. Statement on Auditing Standards (SAS) No. 82 specifies that auditors have a responsibility to assess the likelihood of management fraud and identifies specific risk factors that should be considered when making that assessment. Apostolou et al. (2001b) examined how internal and external auditors rate the relative importance of these factors. This study extends Apostolou et al. (2001b) by examining how forensic experts at four Big 5 professional service firms assess the factors specified in SAS No. 82. These assessments produced two different models of relative importance: (a) a statistical model (produced by the Analytic Hierarchy Process); and (b) a subjective model (based on subjects’ assessment of the relative weights). These models are then used to assess the self-insight of and the degree of agreement among the forensic experts. The results indicate that forensic experts have a moderately high degree of self-insight. A moderate to high degree of consensus among experts’ judgments about the relative importance of fraud risk factors was noted.

The current study examines the effect of fraud training on auditors' ability to identify fraud risk factors. This is important because most auditors have little or no direct experience with fraud; thus, research that investigates the potential effect of indirect experience through training is vitally important to fraud detection and audit quality. A total of 369 experienced auditors completed a complex audit simulation task that involved 15 seeded fraud risk red flags. A total of 143 auditors participated in a 30-minute training session focused specifically on fraud risk, while the remaining 226 auditors learned about general internal control risk during this time block. The results indicate that auditors with fraud training identified significantly more red flags and obtained greater knowledge about fraud risk than auditors who did not receive the training. Considering that the fraud training consumed only 30 minutes out of a 64-hour training session, the findings suggest that even modest exposure to fraud training is quite effective.

This study explores the question of whether investors can successfully detect management fraud using a firm's financial statements. Using financial ratios obtained from fraudulent companies’ financial statements, we examine the effectiveness of both logit and discriminant analyses in predicting the likelihood of fraud. Sixty-eight fraudulent companies used in the study are identified from the SEC's Accounting and Auditing Enforcement Releases. Our research design has addressed certain weaknesses present in prior fraud-detection studies. The empirical results suggest that ratio analysis is grossly ineffective in detecting financial statement fraud. We also discuss the implications of our findings on future research.

Effective internal control over financial reporting (ICFR) should either prevent or enable correction of any material misstatement in a firm’s financial statements. Independent auditors, guided by professional standards, prepare an ICFR audit report, which provides a gauge by which the public can evaluate the reliability of a firm’s financial information. A firm manager may be tempted to misstate financial statements if he/she perceives a substantial reward for doing so. This study examines whether managers and firms are rewarded for misstating their financial statements in situations where there are incentives to do so, specifically, when an industry-leading peer is fraudulently inflating its reported earnings. The authors test to see if managers experience an increase in compensation as a result of misstatement. The authors also test to see if their firms benefit from misstating via changes to their cost of capital. Results suggest that neither managers nor their firms benefit from managing earnings by misstating financial statements. These findings are important, because a manager who ex ante understands that misstating will not lead to benefits personally or his/her firm is less likely to misstate in the first place.

Food fraud as intentional deception for economic gain relies on a low-tech food value chain, that applies a ‘paper-and-pencil approach’, unable to provide reliable and trusted data about food products, accompanied processes/activities and actors involved. Such approach has created the information asymmetry that leads to erosion of stakeholders and consumers trust, which in turn discourages cooperation within the food chain by damaging its ability to decrease uncertainty and capability to provide authentic, nutritional, accessible and affordable food for all. Lack of holistic approach, focus on stand-alone measures, lack of proactive measures and undermined role of customers have been major factors behind weaknesses of current anti-fraud measures system. Thus, the process of strong and fast digitalisation enabled by the new emerging technology called Industry 4.0 is a way to provide a shift from food fraud detection to efficient prevention. Therefore, the objective of this chapter is to shed light on current challenges and opportunities associated with Industry 4.0 technology enablers' guardian role in food fraud prevention with the hope to inform future researchers, experts and decision-makers about opportunities opened up by transforming to new cyber-physical-social ecosystem, or better to say ‘self-thinking’ food value chain whose foundations are already under development. The systematic literature network analysis is applied to fulfil the stated objective. Digitalisation and Industry 4.0 can be used to develop a system that is cost effective and ensures data integrity and prevents tampering and single point failure through offering fault tolerance, immutability, trust, transparency and full traceability of the stored transaction records to all agri-food value chain partners. In addition, such approach lays a foundation for adopting new business models, strengthening food chain resilience, sustainability and innovation capacity.