Fraudulent Behavior Research Articles

Self-serving Altruism: Cheating Behavior Camouflaged as "Support" in Breaching the Social Norms

The influence of surrounding conditions can change a person’s behavior, both positive and negative behavior. The negative behavior in question is a behavior that violates applicable social norms. As with the presence of other people who will benefit from fraudulent behavior that occurs. Therefore, the purpose of this study is to identify patterns of fraudulent behavior that tend to escalate under the assumption that others will also benefit. This study used an experimental design with two groups that obtained differences in treatment (individual group vs. partner group). The number of participants was 122 people with a sampling technique, namely random sampling. The results of this study showed that the group that was informed that only participants themselves would receive benefits from each question that could be answered correctly showed lower average results (M = 6.88), when compared to the group that was informed that the benefits obtained would also be felt by partners from participants (M = 11.44). So it can be concluded that if there is profit sharing with others, it increases a person’s tendency to engage in unethical behavior. Keywords: self-serving altruism, experiment, unethical behavior

Machine learning algorithms to prevent fraudulent transactions in real-time

In the rapidly evolving landscape of digital finance, the proliferation of online transactions has been accompanied by a significant increase in fraudulent activities. This paper explores the application of machine learning algorithms to detect and prevent fraudulent transactions in real-time, thereby enhancing the security and reliability of financial systems. We investigate various machine learning techniques, including supervised learning models such as Random Forest, Logistic Regression, and Neural Networks, as well as unsupervised methods like anomaly detection. By leveraging these algorithms, we aim to identify patterns and anomalies indicative of fraudulent behavior. Our approach integrates robust preprocessing techniques and real-time data analysis to ensure high accuracy and efficiency. The results demonstrate that machine learning models can significantly reduce the incidence of fraud, providing financial institutions with a powerful tool to safeguard their customers’ assets. This study underscores the potential of machine learning to transform fraud detection, offering a scalable and adaptive solution to one of the most pressing challenges in the financial sector

The impact of U.S. economic sanctions on corporate innovation and fraud

AbstractEconomic sanctions have increasingly become a pivotal tool in modern foreign policy, especially in the context of U.S. international strategy. Despite their growing significance, there is a notable lack of empirical research on how these sanctions affect corporate behavior. This study aims to explore the impact of U.S. economic sanctions on innovation and fraudulent activities within Iranian firms subjected to these measures. Utilizing a difference‐in‐differences approach, the findings reveal a weak and negative relationship between sanctions and innovation, while no significant link is found between sanctions and fraudulent activities. Notably, the study uncovers a substantial divergence in companies' responses to sanctions based on their innovation background. Companies with a strong innovation background experience a significant increase in innovation efforts and a corresponding decline in fraudulent behavior upon facing sanctions. In contrast, companies lacking an established innovation background exhibit a reduction in innovation and, in turn, an escalation in fraudulent practices in response to sanctions. These findings remain robust across various sensitivity analyses. This research contributes to the expanding body of empirical literature on sanction outcomes by highlighting the profound impact of innovation background on the responsible and ethical decisions made by sanctioned companies.

The present scenario of artificial intelligence and machine learning in financial services: An empirical study

The financial services industry is experiencing a swift adoption of artificial intelligence (AI) and machine learning for a variety of applications. These technologies can be employed by both public and private sector entities to ensure adherence to regulatory requirements, monitor activities, evaluate data accuracy, and identify instances of fraudulent behavior. The utilization of artificial intelligence (AI) and machine learning (ML) has the potential to provide novel and unforeseen manifestations of interconnectivity within financial markets and institutions. This can be represented by the adoption of previously disparate data sources by diverse institutions. The researchers employed convenience sampling as the sampling method. The form was filled out over the period spanning from July 2023 to February 2024, and it was designed to be both anonymous and accessible through online and offline platforms. To assess the reliability and validity of the measurement scales and evaluate the structural model, we employed Partial Least Squares (PLS) for model validation. Specifically, we have used the software package Smart-PLS 3 with a bootstrapping of 5000 samples to estimate the significance of the parameters. The results indicate a positive and direct connection between artificial intelligence (AI) and either financial services or financial institutions. On the contrary, machine learning (ML) exhibits a strong and positive association among financial services and financial institutions. Similarly, there exists a positive and direct connection between AI and investors, as well as between ML and investors.

Research on Fraud Detection Method of Financial Data of Listed Companies Based on HMCRAN

This study investigates the application of deep learning technology to improve accuracy and efficiency in detecting financial fraud in listed companies. Using data from the China Economic and Financial Research Database on Main Board A-share listed companies with disclosed fraudulent behaviors, a hybrid multi-channel residual attention network (HMCRAN) was constructed, combining multi-channel residual networks and transformers. The study involved feature extraction, data preprocessing, model training, and performance evaluation, validating the superiority of the HMCRAN model for financial fraud detection. Experimental results demonstrate that the model excels in handling high-dimensional financial data and capturing long-term dependencies, significantly improving detection accuracy and robustness. The HMCRAN model outperforms traditional machine learning methods across various evaluation metrics, demonstrating its high practical application value.

Budget participation and financial information asymmetry: Behavior of budget users and financial report fraud

Financial statement fraud is a problem often faced by organizations that can reduce their performance. An organization that successfully achieves its goals must be aware of information asymmetry and the need for moral justice in managing its finances. The research population comprises employees of the finance, planning, reporting, and budget preparation sections of the Gowa Regency regional performance unit. This research selected a saturated sample of 76 employees from the total population. The results show that participatory budgeting has a significant effect on financial report fraud and that information asymmetry has a substantial influence on financial statement fraud. The research results show that moral justice moderates the effect of participatory budgeting on financial report fraud. Moral justice cannot moderate the influence of information asymmetry on financial statement fraud. Employees must still have good moral justice in participatory budgeting to minimize the possibility of fraudulent financial reports. It is hoped that the findings of this research will enable organizations to create innovative information facilities to reduce information asymmetry so that organizational performance can be achieved.

Study on Audit Risk Model Based on Data Mining Algorithm

With the widespread application of modern information technologies such as big data, enterprises have generated a large amount of data in their daily operations. The traditional audit methods have drawbacks such as high cost and high consumption, and can no longer meet the needs of audit work in the digital era. Therefore, it is urgent to adopt audit methods suitable for the digital era to improve audit quality and reduce enterprise Audit risk. For professional auditors in enterprises, it is very important to utilize emerging technologies such as data mining algorithms. The audited enterprise may tamper with its financial statements, and identifying high-quality audit data from massive amounts of data is a huge challenge. Compared to traditional audit methods, data mining algorithms can significantly improve the efficiency and accuracy of audit work. For example, the BP neural network, with its powerful nonlinear mapping ability, can capture complex relationships in data; Support vector machines classify data by finding the optimal hyperplane in high-dimensional space and have good generalization ability; random forest reduces overfitting and improves prediction accuracy by integrating multiple decision trees; Association rule algorithms can discover interesting relationships between data items, helping auditors identify potential fraudulent behavior or abnormal transactions. Therefore, the purpose of this study is to accurately evaluate and reduce the audit risk of enterprises, and to build an audit risk model using computer data mining algorithms. This provides necessary reference and guidance for auditors to conduct data analysis and mine valuable data during the audit process of enterprises, thereby improving audit efficiency.

Provisional Attachment on the Documentary Letters of Credit: A Comparative Study Saudi and Emirati Law

The study aims to study the provisional attachment of documentary letters of credit to prevent the beneficiary from liquidating the value of the credit as the beneficiary used fraudulent methods without which he would not have been able to obtain the value of the credit. The study follows the descriptive analytical comparative approach. It will discuss the legislative and judicial efforts related to the provisional attachment of documentary letters of credit. This will lead us to the comparative approach to comparing what is stated in Emirati and Saudi law and the judgments. The study concludes several findings, including that documentary letters of credit are an unquestionable means of success in international trade operations, especially since they discuss the problems of geographical distance between the seller and the buyer. However, fraudulent behaviors by sellers (beneficiaries of the documentary letters of credit) disrupt the dominance of documentary letters of credit as the most important means of payment in international trade transactions. The study concludes with several recommendations, namely: the necessity of adopting the Uniform Customs and Practice (UCP) for Documentary Letters of Credit as a rule to eliminate instances of fraud in its transactions.

Harnessing AI for Next-Generation Financial Fraud Detection: A Data-Driven Revolution

Artificial Intelligence in Financial Fraud Detection: A Comprehensive Approach to Enhancing Financial Security The rise of artificial intelligence (AI) offers an opportunity to significantly strengthen financial security by combating financial fraud, which has become increasingly complex and widespread. Traditional detection methods are often insufficient in identifying and preventing fraudulent activities, prompting a shift towards AI-based solutions. This study explores the application of AI, particularly machine learning algorithms, in improving the accuracy and efficiency of fraud detection. By analyzing large financial datasets, AI can detect anomalies that may indicate fraudulent behavior more effectively than traditional approaches. This research adopts a two-phase methodology. The first phase involves a thorough review of existing financial fraud detection methods, comparing traditional techniques with AI-based models to identify gaps. Various machine learning approaches, including supervised, unsupervised, and deep learning algorithms, are reviewed for their effectiveness in detecting fraud. The second phase involves developing and testing an AI model to identify fraudulent patterns within transactional data. The model uses machine learning algorithms to process vast datasets and detect deviations from typical financial behaviors, flagging potentially fraudulent activities. The expected results indicate that AI systems can outperform traditional fraud detection methods by significantly reducing false positives and improving the detection rate of genuine fraud. This reduction in false positives is vital for financial institutions, as it reduces unnecessary investigations and saves valuable resources. Additionally, enhanced fraud detection protects both institutions and consumers from financial losses.The findings of this study aim to provide financial institutions with practical insights into the implementation of AI-driven fraud detection systems. Furthermore, the research highlights the need for continuous refinement of AI models to adapt to the evolving nature of financial fraud. By leveraging AI technologies, financial institutions can revolutionize their approach to fraud detection, making financial systems more secure and responsive to emerging threats.

Graph neural network for fraud detection via context encoding and adaptive aggregation

Financial fraud is a vital issue which causes considerable economic losses for financial institutions. Existing studies apply various methods to detect fraudsters from financial data. In particular, methods based on Graph Neural Networks(GNNs) are among the most effective. However, applying graph neural networks to fraud detection still faces challenges of capturing two types of fraudulent behaviors: the context-related behavior and camouflage-related behavior. To address the challenges, we present Context-encoding-and-Adaptive-aggregation-based Fraud Detector(CAFD), a novel GNN-based fraud detection model. To capture the context-related fraudulent behavior, we devise a context encoding module which encodes the time intervals of out-edges and out-degree for each node in the graph. In addition, we design an adaptive aggregator which identifies the camouflage-related behavior by performing random dropping on messages during the message passing process of GNNs. We evaluate the performance of CAFD with extensive experiments on two real-world datasets. Results of the experiments demonstrate that our model outperforms state-of-the-art baselines.

Promised hassle time management in online retailing with fraudulent and regretful customers

Fraudulent customer return behavior, called “wardrobing,” incurs significant product return costs for online retailers. However, customers can also behave regretfully in online retailing, causing high product return costs. Consequently, we explore the combined effect of fraudulent and regretful customers in product returns. Research suggests implementing restrictive return policies to curb huge return costs due to fraudulent and regretful customer behaviors. One of the ways to implement a restrictive policy is by introducing hassle time. Consequently, retailers commit promised hassle times to customers, during which the retailers can approve the product returns and issue refunds. As a result, we determine how an online retailer can respond to regretful and fraudulent customers through promised hassle time while considering the stochastic nature of hassle time. In some situations, an online retailer might know that hassle time follows a specific probability distribution; in others, a retailer might not know the distribution. Therefore, we determine the optimal promised hassle time an online retailer must promise to regretful and fraudulent customers in each situation. For the first situation, we determine that a specific ratio, which we call the customer ratio, determines how the optimal promised hassle time changes with customers' fraud and regret levels. If the customer ratio is one, the optimal promised hassle time does not change; if it is greater than one, the optimal promised hassle time increases; and if it is less than one, the optimal promised hassle time decreases, with an increase in fraud and a decrease in regret levels. For the second situation, we propose a novel decision-making tool for online retailers, enabling them to optimize the promised hassle time. Finally, we generalize the results of our study to order cancellations with regretful customers, and shared mobility services.

Fake It Till You Make It—A Statistical Assessment of the Proportion of Fake Reviews in Closed Reputation Systems

ABSTRACT Fake reviews have become an increasingly relevant issue in electronic commerce. Regulators and platform operators have begun to take action against fake reviews through regulation and litigation. While there has emerged an ample body of research on fake reviews in open reputation systems (i.e. where everyone can write reviews), little is known about the frequency and nature of fake reviews in closed reputation systems (i.e. where the completion of a transaction is a necessary precondition for reviewing). This article assesses the frequency of fake reviews in this particular domain of the platform economy. To do so, we draw on data from Airbnb and investigate systematic differences between first and second rating score distributions, estimating the proportion of potentially fake five-star ratings using KL-divergence. In doing so, we advance the understanding of fake reviews in closed reputation systems, offering theoretical insights into review dynamics and practical strategies for detecting fraudulent behavior using score distributions and user attributes. This shows that early-on reputation is crucial for complementors to overcome the cold-start problem, and platform operators will have to think of ways to allow them to do so (e.g. reputation imports) in order not to jeopardize the overall credibility of their reputation systems.

Analysis of the Influence of Diamond Fraud, Integrity, and Religiosity on Academic Fraud Behavior

This study aims to determine the effect of pressure, opportunity, rationalization, capability, integrity, and religiosity on academic cheating behaviour in undergraduate accounting students from Islamic-based universities in Semarang. This research is included in the comparative causal research. The population of this study was undergraduate accounting students from Islamic-based universities in the city of Semarang, namely Universitas Islam Sultan Agung, Muhammadiyah University, Wahid Hasyim University, and UIN Walisongo Semarang. The sampling technique used was purposive sampling. The sample used in this study was 60 students. The data analysis techniques used are descriptive statistics, data quality test, classical assumption test, multiple linear regression analysis, model goodness test, and individual parameter significance test. Pressure has been proven to positively and significantly affect the academic cheating behaviour of accounting students from Islamic-based universities in Semarang. Pressure is proven to have a positive and significant effect. Opportunity is proven to have a positive and significant effect. Rationalization is proven to have a positive and significant effect. Ability is not proven to have a significant effect. Integrity has yet to be proven to have a significant effect. This means that high integrity does not influence students to suppress academic cheating behaviour. Religiosity has not been proven to significantly affect the academic cheating behaviour of accounting students at Islamic-based colleges in Semarang City. This means that high religiosity does not influence students to suppress academic cheating behaviour.

The Impact of Machine Learning on Gaming Security

The gaming business has been seeing tremendous expansion in recent years, which can be attributed to the convergence of technological breakthroughs and an ever-expanding user base respectively. As the gaming business continues to develop, the security risks that target gaming platforms also continue to improve. As a result, it is very necessary to implement advanced protection measures. The use of machine learning (ML) has emerged as a transformational force in the enhancement of gaming security. It provides novel ways to tackle a variety of cyber threats and ensures that players have a gaming experience that is both secure and fair. The purpose of this study is to investigate the influence that machine learning has on gaming security, with a particular emphasis on its applications, strengths, and weaknesses.Gaming firms are rethinking their approach to security problems as a result of the use of machine learning algorithms, especially those that make use of artificial intelligence (AI). One of the most important uses of machine learning in gaming security is the detection and prevention of fraudulent activity. When it comes to keeping up with the ever-evolving strategies used by fraudsters, traditional rule-based systems sometimes suffer. On the other hand, machine learning algorithms are able to examine enormous volumes of data and recognise patterns that are suggestive of fraudulent behaviour. This enables real-time identification and prevention of fraudulent actions such as account takeovers, cheating, and other malevolent acts.

Information Systems and Mechanism for Prevention of Cyber Frauds

Cyber criminals are targeting online frauds, exploiting anonymity to deceive. They use fake websites, fake ads and stolen credit or debit cards for purchases. Bank frauds, despite high-speed processing and technical assistance, can damage a bank's reputation and operational efficiency, necessitating a strong emphasis on business ethics in the banking sector. The machine learning and artificial intelligence enhance online security of information systems. US enforces anti-trust laws and promotes stakeholder rights, addressing fraud and identity theft through safety tips and civil law implementation. Cyber criminals steal personal information for unauthorized purchases, identity theft, and fraudulent activities. Machine learning and artificial intelligence can enhance online security and user awareness. AI-based threat detection analyzes network activity for cyberattacks, limiting damage. Multi-Factor Authentication (MFA) combines traditional passwords with biometric authentication for enhanced security. The application of Big Data systems allows administrations for the collection and analysis of Data and its storage obtained from various sources, using platforms like Hadoop, Apache Spark, and Kafka for real-time processing and data analytics. Digital devices are increasingly being used in banking frauds, posing significant risks to both customers and the banking sector, necessitating stricter regulations and enforcement measures. Common banking sector issues include negligent, fraudulent, and deviant behavior, affecting various functions of getting, gathering, transporting, disbursing, loaning, trading, capitalizing, replacing, and servicing money-claims domestically and internationally. This paper discusses machine learning and anomaly detection techniques for preventing fraud in online payment systems, including behavioral profiling and Bagged Decision Tree models along with other methods.

Credit Card Fraud Detection Using Machine Learning Algorithms

This study aims to address the rising issue of credit card fraud by developing a machine learning model capable of identifying and preventing fraudulent transactions. The model works by analyzing transaction data to detect potential fraud, subsequently canceling the transaction and alerting the credit card owner. Credit card fraud detection is a classification problem, where various machine learning algorithms are applied to distinguish between legitimate and fraudulent transactions. The analysis emphasizes the importance of robust countermeasures due to the increasing use of credit cards globally. However, real-world implementation of such systems may face challenges, particularly in securing the cooperation of banks and addressing resource constraints. The study also highlights key dataset features that correlate with fraudulent behavior, with ensemble methods standing out as top-performing algorithms in terms of accuracy and efficiency.

Pengaruh Fraud Pentagon Dan Tingkat Suku Bunga Terhadap Kecurangan Laporan Keuangan Pada Perusahaan Consumer Cyclicals Yang Terdaftar di Bursa Efek Indonesia Tahun 2020-2022

This study aims to analyze the effect of fraud pentagon and interest rate levels on financial statement fraud in consumer cyclical companies listed on the Indonesia Stock Exchange (IDX) in 2020-2022. Fraud pentagon, which consists of pressure, opportunity, rationalization, capability, and arrogance, is the main focus to see how each element affects the potential for fraud in the company's financial statements. Interest rates are also analyzed as external variables that can contribute to financial pressure and encourage fraudulent behavior. The method in this study uses quantitative analysis. This study uses a purposive sampling technique to select samples, so that 12 consumer cyclical companies were obtained with a research period from 2020-2022. The data analysis technique applied is multiple linear regression, with hypothesis testing using the T-test, F-test, and coefficient of determination, all carried out using SPSS software version 26. The results of this study indicate that, overall, the variables External Pressure, Nature of Industry, Change of Director, and interest rates have a significant effect on financial reporting fraud in consumer cyclical companies listed on the Indonesia Stock Exchange during the 2020-2022 period. However, a separate analysis shows that the variables Change in Auditor and Frequent Number of CEO's Picture (CEOPIC) do not show a significant effect on financial reporting fraud in these companies during the same period.

Research on Financial Fraud Based on Changyuan Group's Acquisition of Changyuan and Eagle

In recent years, with the development of the China’s economy, in order to seek business growth points, the number of mergers and acquisitions of enterprises has increased rapidly. In the process of mergers and acquisitions, there are often some financial fraud behaviors, such as fictitious income and false statements, to push up the merger and acquisition premium, which will greatly damage the stability of the financial market and the legitimate rights and interests of investors. This paper adopts the financial fraud case of Changyuan Group's acquisition of Shanghai Heying Electromechanical Technology Co., LTD. in 2016 as an example, and combines the fraud triangle theory to analyze the motivation of financial fraud. According to the punishment announcement and other information, this paper analyzes the identification of financial fraud information with a three-dimensional model, analyzes and presents the consequences of financial fraud, and proposes the suggestions and enlightenment for subsequent M&A cases.

The Effect of Diamond Fraud on Academic Fraud Behavior

The study aims to address the impact of Pressure, Opportunity, Rationalization, and Capability on academic cheating behavior with academic integrity as moderated variables on scholarship students at Economic and Business Faculty, Djuanda University. The study was a descriptive quantitative study that used primary data with a number of 106 students obtained with saturated sampling techniques. The data analysis techniques performed in this study are either MRA or moderated regression analysis made using SPSS. Studies have concluded that Pressure, Rationalization, and Capability have an impact on academic cheating behavior, while Opportunity has no effect on academic cheating behavior. Furthermore, Rationalizing also has an effect on academic cheating behavior with academic integrity as moderate variables, while Pressure, Opportunity, and Capability have no effect on academic cheating behavior with academic integrity as a moderation variable.

The Unintended Consequences of Home-Buying Restriction in China

Abstract We investigate the fake divorce activities associated with the home-buying restriction policy in China. We find that the policy increased divorce rate (marriage restoration rate) in the treated cities by 0.436 (0.195) permillage point relative to the control cities. This explains a 19.9% increase in the overall national divorce rate, of which at least 45% can be interpreted as fake divorces. Moreover, we find that the main responders to this policy are people who are older, childless, less-educated, and wealthier. Finally, we show that the fraudulent behavior has significant implications for market efficiency, intra- and inter-household wealth inequality, and other consequences.