Financial Fraud Research Articles

The role of artificial intelligence in auditing and fraud detection in accounting information systems: moderating role of natural language processing

Purpose This study aims to investigate the moderating role of natural language processing natural language processing (NLP) on the relationship between AI-empowered AIS (data gathering, data analysis, risk assessment, detection, prevention and Investigation) and auditing and fraud detection. Design/methodology/approach Quantitative methodology was adapted through a questionnaire. In total, 221 individuals represented the population of the study, and SPSS was used to screen primary data. The study indicated the acceptance of the hypothesis that “Artificial Intelligence in AIS has a statistically significant influence on auditing and fraud detection,” showing a strong correlation between auditing and fraud detection. The study concluded that NLP moderates the relationship between AI in AIS and auditing and fraud detection. Findings The study’s implications lie in its contribution to the development of theoretical models that explore the complementary attributes of AI and NLP in detecting financial fraud. Research limitations/implications A cross-sectional design is a limitation. Practical implications NLP is a useful tool for developing more efficient methods for detecting fraudulent activities and audit risks. Originality/value The study’s originality stems from its focus on the use of AI-empowered AIS, a relatively new technology that has the potential to significantly impact auditing and fraud detection processes within the accounting field.

Scam Call Detection Using NLP and Naïve Bayes Classifier

Financial fraud, particularly credit card fraud, is a pressing concern in the realm of digital transactions. The number of phone scams is increasing daily as con artists use phone calls to target victims for nefarious ends. Individuals are falling for con artists' proposals, becoming victims and giving up their personal information, leaving them open to abuse. Effective detection techniques are becoming more and more necessary. In this study, we offer an efficient approach to scam call identification utilizing speech-to-text libraries and the machine learning technique Naïve Bayes classifier. Our technology, which translates voice to text, uses this text to evaluate conversations in real time. It looks for trends and suspicious phrases that point to attempted scams, including asking for credit card numbers, passwords, or other sensitive information. The user will be able to decide whether or not to trust and continue with the call by using the alert prompt that appears as a pop-up message if the words are found to be suspicious. The user will take certain measures, such as ending the conversation right away, blocking the number, and reporting it further, if they don't trust the call. Our strategy is to successfully handle scam calls through ongoing adaptation and learning, boosting user security and confidence in phone conversations. The user will be able to decide whether or not to trust and continue with the call by using the alert prompt that appears as a pop-up message if the words are found to be suspicious. The user will take certain measures, such as ending the conversation right away, blocking the number, and reporting it further, if they don't trust the call. Our strategy is to successfully handle scam calls through ongoing adaptation and learning, boosting user security and confidence in phone conversations. Keyword: Spam Detection, Naïve Bayes, Natural Language Processing, Machine Learning.

Optimizing fraud detection in financial transactions with machine learning and imbalance mitigation

AbstractThe rapid advancement of the Internet and digital payments has transformed the landscape of financial transactions, leading to both technological progress and an alarming rise in cybercrime. This study addresses the critical issue of financial fraud detection in the era of digital payments, focusing on enhancing operational risk frameworks to mitigate the increasing threats. The objective is to improve the predictive performance of fraud detection systems using machine learning techniques. The methodology involves a comprehensive data preprocessing and model creation process, including one‐hot encoding, feature selection, sampling, standardization, and tokenization. Six machine learning models are employed for fraud detection, and their hyperparameters are optimized. Evaluation metrics such as accuracy, precision, recall, and F1‐score are used to assess model performance. Results reveal that XGBoost and Random Forest outperform other models, achieving a balance between false positives and false negatives. The study meets the requirements for fraud detection systems, ensuring accuracy, scalability, adaptability, and explainability. This paper provides valuable insights into the efficacy of machine learning models for financial fraud detection and emphasizes the importance of striking a balance between false positives and false negatives.

DyHDGE: Dynamic heterogeneous transaction graph embedding for safety-centric fraud detection in financial scenarios

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.

Is it a matter of governance or judicial favoritism? Legal expertise at an executive level and its use in cases of corporate financial fraud

This study examines how executives’ legal expertise affects corporate financial fraud and the mechanism behind this using data from A-listed companies between 2011 and 2021. Findings show a positive correlation between executives’ legal backgrounds and corporate financial fraud, which is mainly driven by external audit quality and corporate social responsibility. This finding provides evidence of how the law affects small-scale corporate governance. This study emphasizes the value of firms leveraging their executives’ legal background, which helps regulators identify potential hazards in corporations.

An Intelligent Financial Fraud Detection Model Using Knowledge Graph-Integrated Deep Neural Network

Financial fraud detection has been an urgent technical demand in cyberspace. It highly relies on clear extraction and deep representation toward complex relationships inside financial social networks. As consequence, this study combines both knowledge graph and deep learning to deal with such issue. Thus, an intelligent financial fraud detection model based on knowledge graph guidance and deep neural network is proposed in this paper. First, a new knowledge graph based on financially related systems is constructed, which includes multiple entities and relationships. Then, an adversarial learning-based neural network structure is formulated to extract financial attributes. Finally, the detection results can be output according to the extracted factors. Empirically, the proposal is implemented on a real-world dataset for performance evaluation. The experimental results show that it has higher accuracy and effectiveness compared to traditional fraud detection methods. The proposed detection model can not only identify known fraudulent behaviors, but also predict potential fraud patterns based on consumer habits, thereby improving the security and reliability of financial transactions. It can also update the knowledge graph in real-time, enabling it to cope with emerging fraud methods and variants.

Research on Legal Issues of Financial Fraud in Listed Companies

Research on Legal Issues of Financial Fraud in Listed Companies

Implementation of Big Data Analysis Technology to Improve Decision Making in the Accounting Field

This article explores the Implementation of Big Data Analysis Technology to Enhance Decision Making in the Accounting Field. With the exponential growth of data, accounting professionals face challenges in processing and extracting meaningful insights. The study delves into the integration of advanced analytics tools within accounting practices to harness the potential of big data. The research begins by examining the current landscape of the accounting field and the traditional decision-making processes. It identifies the limitations and inefficiencies in handling vast amounts of financial data. Subsequently, the article elucidates the pivotal role of big data technologies in revolutionizing accounting practices. By employing sophisticated algorithms and data processing techniques, accountants can gain deeper insights into financial trends, risk factors, and performance metrics. Moreover, the study investigates real-world implementations of big data analytics in accounting firms. It highlights success stories and challenges faced during the transition, shedding light on the practical implications of adopting such technologies. The article emphasizes the importance of skill development among accounting professionals to effectively navigate and utilize big data tools. Furthermore, the impact of big data analysis on decision-making accuracy and efficiency is scrutinized. The findings underscore the potential for improved financial forecasting, fraud detection, and strategic planning. The integration of big data analytics is positioned as a catalyst for more informed and timely decision-making in the dynamic landscape of accounting. In conclusion, this research contributes to the evolving discourse on the intersection of big data technology and accounting. It provides valuable insights into the transformative potential of implementing advanced analytics tools, ultimately enhancing decision-making processes within the accounting field.

Why cartel participation leads to financial statement fraud and market abuse

ABSTRACT In an attempt to hide from the competition authorities colluding firms risk committing financial statement fraud and market abuse. When colluding managers set the conditions for their cartel the resulting increase in profitability and ability to pay outstanding debt enables the firms to attract more investors, get access to larger loans and at a lower interest rate. The natural reluctance to disclose the firm’s cartel participation creates financial reports with misleading content, increases the likelihood of insider dealing and the ability to attract more funds diverts needed capital from otherwise more eligible firms and will endanger the integrity and efficient functioning of the financial markets. The conclusion is that firms and individuals involved in cartel offences should be investigated for financial statement fraud and market abuse although when persons may be subject to criminal sanctions it will decrease the attractiveness for individuals to use the leniency framework.

Financial crimes in Africa and economic growth: Implications for achieving sustainable development goals (SDGs)

AbstractThe current review systematically synthesizes existing literature to provide a comprehensive overview of the nature of financial crimes in Africa and their impact on economic growth. We adopted the PRISMA protocol to identify 128 papers from the Scopus database, which were analyzed using MS Excel, VOSviewer, and R‐packages (Bibliometrix). The survey reveals that financial crimes are on the rise in Africa and have gained increasing concern over the years on the part of scholars, governments, and NGOs. The survey also demonstrates that most of the financial crime in Africa emanates from illicit activities such as credit card fraud, cybercrime, mobile money fraud, financial statement fraud, Ponzi scheme, bribery and corruption, public fund mismanagement, terror financing, piracy, identity fraud, tax invasion, drug trafficking, product based‐fraud, burglary, trade‐based money laundering, sex marketing, and gambling; with the majority occurring in specific regions like Western Africa, Southern Africa, and Eastern Africa. Sociopolitical marginalization, poverty, and unemployment, weak institutional and financial regulatory systems and individual selfish interests were the major causes. Overall, the content analysis of the studies indicates that financial crimes have significant negative impacts on the economic growth of the African continent. Implications for future research and practices have been discussed.

Abnormal Behavior Recognition Based on 3D Dense Connections.

Abnormal behavior recognition is an important technology used to detect and identify activities or events that deviate from normal behavior patterns. It has wide applications in various fields such as network security, financial fraud detection, and video surveillance. In recent years, Deep Convolution Networks (ConvNets) have been widely applied in abnormal behavior recognition algorithms and have achieved significant results. However, existing abnormal behavior detection algorithms mainly focus on improving the accuracy of the algorithms and have not explored the real-time nature of abnormal behavior recognition. This is crucial to quickly identify abnormal behavior in public places and improve urban public safety. Therefore, this paper proposes an abnormal behavior recognition algorithm based on three-dimensional (3D) dense connections. The proposed algorithm uses a multi-instance learning strategy to classify various types of abnormal behaviors, and employs dense connection modules and soft-threshold attention mechanisms to reduce the model's parameter count and enhance network computational efficiency. Finally, redundant information in the sequence is reduced by attention allocation to mitigate its negative impact on recognition results. Experimental verification shows that our method achieves a recognition accuracy of 95.61% on the UCF-crime dataset. Comparative experiments demonstrate that our model has strong performance in terms of recognition accuracy and speed.

Research on Financial Fraud of Selen Technology

China's Construction of High-quality Capital Market Holds Zero Tolerance to Financial Fraud of Listed Companies. Selen Technology was listed on the Shenzhen Stock Exchange in 2010. In 2020, it was disclosed by the CSRC that it had engaged in financial fraud for three consecutive years from 2016 to 2018, with inflated profits of up to RMB180 million. In this paper, Selen Technology is selected as a case company, and the motivation, means and causes of financial fraud are analyzed based on fraud triangle theory, and the corresponding governance measures are given.

Financial Fraud. Challenges and Solutions for Financial Auditing and Accounting Professionals – a Bibliometric Research

Financial Fraud. Challenges and Solutions for Financial Auditing and Accounting Professionals – a Bibliometric Research

ML-Based Online Transaction Fraud Detection

This paper focuses on fraud detection and the measures necessary to fully automate this process, which has become crucial for banks. With fraud on the rise, it poses significant threats and can result in substantial damages to financial institutions. Transaction data presents unique challenges for fraud detection due to the lack of short-term processing capabilities. The primary objective is to conduct a feasibility study on the selected fraud detection methods. Using various models, we aim to test each transaction individually and proceed accordingly.Initially, we define the detection task, outlining the dataset attributes, metric choices, and techniques to manage unbalanced datasets. This analysis helps identify underlying patterns within the dataset, such as how cardholders' purchasing habits may evolve over time and how fraudsters may adapt their tactics. We then explore various methods used to derive sequential features from credit card transactions. Financial fraud, the practice of gaining financial benefits through deceitful and unlawful means, has become a significant threat to businesses and organizations. Despite numerous efforts to combat financial fraud, it continues to inflict substantial economic and societal harm, with daily losses reaching significant amounts. Traditional methods for fraud detection, introduced years ago, were predominantly manual, making them time- consuming, costly, and prone to errors. Although more research is being conducted, current approaches have not effectively reduced the financial losses associated with fraud. Conventional fraud detection methods, such as manual verifications and inspections, are inefficient, costly, and inaccurate. Keywords: Transaction data, cardholders' purchasing.

The use of machine learning algorithms to predict financial statement fraud

The use of machine learning algorithms to predict financial statement fraud

Financial fraud detection for Chinese listed firms: Does managers' abnormal tone matter?

This study introduces a novel perspective on financial fraud detection by exploring the utility of managers' abnormal tone. To mitigate bias in indicator selection, we implement a feature selection process involving a comprehensive set of 301 indicators, including financial, non-financial, and textual, and various machine learning algorithms. The dataset contains 6077 pairs of fraudulent and non-fraudulent samples in China. Our findings underscore the significance of abnormal tone in fraud detection, establishing it as a prominent factor in the feature selection process. The accuracy outcomes from eight machine learning models further confirm that incorporating abnormal tone can enhance fraud detection performance.

The Impact of Artificial Intelligence on Financial Markets and Business Operations

The integration of artificial intelligence (AI) in financial markets and business operations has emerged as a transformative force, reshaping traditional practices and unlocking new opportunities. This paper presents a systematic literature review encompassing a wide array of studies on AI applications in finance and business. The review explores AI's role in enhancing financial forecasting, trading strategies, risk management, and fraud detection. It discusses various AI techniques such as machine learning, deep learning, and natural language processing, highlighting their effectiveness in analysing vast datasets and improving decision-making processes. Moreover, the review addresses the implications of AI adoption in optimising business operations, including process automation, predictive analytics, and customer experience enhancement. Key themes include the benefits of AI-driven innovations, such as increased efficiency, cost reduction, and personalised services, alongside challenges related to job displacement, algorithmic bias, and regulatory frameworks. The paper concludes with insights into future research directions aimed at advancing AI's interpretability, transparency, and ethical deployment in financial and business contexts.

AI-based financial transaction monitoring and fraud prevention with behaviour prediction

AI-based financial transaction monitoring and fraud prevention with behaviour prediction

Do the fraud triangle components fuel complex financial fraud? A study of nonfinancial firms in Pakistan

Purpose Financial fraud is a severe corporate fraud committed for achieving various objectives, like attaining financial targets, lowering debt and providing good signals to the market. Such financial fraud deceives stakeholders and results in substantial financial losses. This study aims to detect financial fraud using the modified Beneish M-Score, the most appropriate forensic tool for fraud detection. Furthermore, the current study also examines the influential role of the fraud triangle’s elements (pressure, opportunity and rationalization) on financial fraud in nonfinancial firms during 2018–2021, offering insight for understanding and mitigating fraudulent activities in the corporate world. Design/methodology/approach Financial fraud is treated as a dependent variable measured through a modified Beneish M-score, while the fraud triangle elements (pressure, opportunity and rationalization) are measured through six proxies, which are financial stability, leverage, financial target, nature of the industry, the effectiveness of supervision and auditor changes. Findings The study's finding proclaimed that fraud triangle elements result in financial fraud. Findings unveil that all elements (pressure, opportunity and rationalization) of the fraud triangle significantly influence financial fraud. The study confirms that these elements must be considered to protect investors and provide a safe environment for investment. Originality/value Rare literature found addressing the detection of financial fraud and its nexus with the fraud triangle specifically in Pakistan where deficient governance is notably prevalent. This study attempts to fill such a gap and contribute to knowledge.

Implementing machine learning algorithms to detect and prevent financial fraud in real-time

Implementing machine learning algorithms to detect and prevent financial fraud in real-time