Fraud Detection Research Articles

Finance Modeling Approach Using Machine Learning

The integration of machine learning (ML) into financial modeling represents a transformative shift in the finance sector, enhancing analytical capabilities and decision-making processes. This article explores the fundamental concepts of financial modeling and machine learning, illustrating how ML methodologies—both supervised and unsupervised—improve traditional financial models by enabling the analysis of extensive datasets to uncover intricate patterns. By leveraging historical data, ML enhances predictive accuracy in various applications, including risk assessment, algorithmic trading, credit scoring, and fraud detection. The article highlights significant advancements in predictive analytics through techniques such as regression analysis and time series forecasting, which allow financial analysts to navigate market uncertainties more effectively. Moreover, the automation of data processing and feature engineering through ML leads to increased operational efficiency, reducing human error and enhancing real-time decision-making capabilities. However, challenges such as data quality issues, model interpretability, and ethical considerations regarding algorithmic bias necessitate careful management to ensure responsible implementation. The article emphasizes the importance of transparency in ML models to foster trust among stakeholders while meeting regulatory requirements. Future research directions are proposed, focusing on the integration of explainable AI with blockchain technology and the implications of big data analytics on ML models. By addressing these emerging challenges and opportunities, finance professionals can leverage advanced analytical tools to drive innovation and enhance strategic initiatives in an increasingly complex financial landscape. Ultimately, this article underscores the pivotal role of machine learning in reshaping financial modeling practices and its potential to redefine the future of finance.

The Role of AI and Machine Learning in Fraud Detection: Enhancing Risk Management in Corporate Finance

The Role of AI and Machine Learning in Fraud Detection: Enhancing Risk Management in Corporate Finance

Analysis of species adulteration in beef sausage using real-time polymerase chain reaction in Makassar, Indonesia

Background and Aim: Adulteration, or the inclusion of meats not declared on the label of processed meat products, constitutes a fraudulent practice that poses a threat to public health. Sausages, which are processed meats derived from a blend of minced meats that obscure the original muscle’s morphological features, are particularly prone to adulteration, making the visual detection of fraud more challenging. The research aimed to detect and measure the proportion of pork, chicken, buffalo, and beef DNA in commercially available processed meat packaged, labeled, and sold as “beef sausages” in Makassar, Indonesia. Materials and Methods: A total of 30 beef sausage samples were collected from traditional and modern markets as well as tourist attractions in Makassar. DNA was isolated and the species were identified using quantitative polymerase chain reaction. Results: The findings revealed that all sausage samples contained not only beef DNA, as indicated on their labels but also undeclared DNA from chicken and buffalo. Notably, pork DNA was not detected in the samples. The frequencies of chicken and buffalo meat were 9.2% and 10%, respectively, whereas it was 0.85% for beef in the beef sausage samples. Conclusion: The discovery of chicken and buffalo species in beef sausage samples indicates adulteration, potentially posing severe quality risks. Keywords: adulteration, beef sausage, deoxyribonucleic acid, polymerase chain reaction, species.

A Spatial–Temporal Gated Network for Credit Card Fraud Detection by Learning Transactional Representations

A Spatial–Temporal Gated Network for Credit Card Fraud Detection by Learning Transactional Representations

Research and Empirical Evidence of Machine Learning based Financial Statement Analysis Methods

This study presents a novel approach called FinAnalytix which merging machine learning’s prowess in pattern recognition with financial statement analysis. This integrated algorithm combines deep neural networks and recurrent neural networks for predictive accuracy in stock return analysis, alongside logistic regression and random forest models for robust fraud detection in financial statements. The empirical evidence demonstrates FinAnalytix effectiveness in identifying abnormal financial patterns and predicting market reactions to earnings announcements. The study utilizes extensive data from listed companies, ensuring a comprehensive and practical application. FinAnalytix represents a significant advancement in the field, providing a dual approach to financial analysis for enhancing investment strategies through accurate stock return forecasts and bolstering financial integrity by detecting fraudulent activities. The simulation of the study based on the financial data of 100 sample listed companies. This research not only bridges the gap between traditional financial analysis and modern machine learning techniques but also offers a powerful tool for investors and regulatory bodies in navigating the complex financial landscape.

ChatGPT: A canary in the coal mine or a parrot in the echo chamber? Detecting fraud with LLM: The case of FTX

Does the paradigm shift brought by Large Language Models (LLMs) hold the promise of revolutionizing financial analysis? Our article tackles this question by exploring fraud detection in cryptocurrency exchanges, with a focus on FTX. We study the abilities of generative artificial intelligence tools like ChatGPT to serve as early-warning systems of fraud and identify red flags in the particular and difficult case where no financial information is available. We recognize several challenges to provide insights beyond human knowledge. To achieve a higher degree of scrutiny, we highlight the role of sequential interactions between the AI Chatbot and the researcher as well as the inclusion of external contents, a technique known as Retrieval Augmented Generation (RAG). Therefore, this article serves as a cautionary tale on the necessary conditions to achieve augmented intelligence.

Artificial Intelligence Enabled Loan Processing – A Boon for Micro Entrepreneurs

Microbusiness entrepreneurs encounter substantial difficulties in obtaining timely and effective financing to grow their companies in the rapidly changing financial landscape. Traditional loan processes are frequently laborious and time-consuming, which limits small businesses' potential for expansion. This study explores how artificial intelligence (AI) has the potential to revolutionise the loan environment for microbusiness owners. AI streamlines loan processing to provide a quicker, more efficient, and fairer method, empowering entrepreneurs to take opportunities and succeed. The study shows how processing gets quicker, more accurate, and inclusive loan by using secondary data sources. Diverse pieces of literature highlight the benefits of AI for credit risk assessment and transparency. Despite difficulties like implementation expenses, AI provides unmatched advantages including less paperwork, greater access, and enhanced fraud detection. Human monitoring ensures moral AI implementation, finding a balance that changes the financial environment for microentrepreneurs.

ADVANCED FRAUD DETECTION IN CARD-BASED FINANCIAL SYSTEMS USING A BIDIRECTIONAL LSTM-GRU ENSEMBLE MODEL

This article addresses the challenges of fraud in card-based financial systems and proposes effective detection and prevention strategies. By leveraging recent data analytics and real-time monitoring, the study aims to enhance transaction security and integrity. The authors review existing fraud detection methodologies, emerging trends, and the evolving tactics of fraudsters, emphasizing the importance of collaboration among financial institutions, regulatory agencies, and technology providers. Our proposed solution is an ensemble model combining Bidirectional Gated Recurrent Unit (BiGRU) and Bidirectional Long Short-Term Memory (BiLSTM) networks, designed to capture complex transactional patterns more effectively. Comparative analysis of six machine learning classifiers—AdaBoost, Naïve Bayes, Decision Tree, Logistic Regression, Random Forest, and Voting—demonstrates that our BiLSTM-BiGRU ensemble model outperforms traditional methods, achieving a fraud detection performance score of 89.22%. This highlights the advanced deep learning model's superior ability to enhance the robustness and reliability of fraud detection systems.

Proactive fraud defense: Machine learning’s evolving role in protecting against online fraud

As online fraud becomes more sophisticated and pervasive, traditional fraud detection methods are struggling to keep pace with the evolving tactics employed by fraudsters. This paper explores the transformative role of machine learning in addressing these challenges by offering more advanced, scalable, and adaptable solutions for fraud detection and prevention. By analyzing key models such as Random Forest, Neural Networks, and Gradient Boosting, this paper highlights the strengths of machine learning in processing vast datasets, identifying intricate fraud patterns, and providing real-time predictions that enable a proactive approach to fraud prevention. Unlike rule-based systems that react after fraud has occurred, machine learning models continuously learn from new data, adapting to emerging fraud schemes and reducing false positives, which ultimately minimizes financial losses. This research emphasizes the potential of machine learning to revolutionize fraud detection frameworks by making them more dynamic, efficient, and capable of handling the growing complexity of fraud across various industries. Future developments in machine learning, including deep learning and hybrid models, are expected to further enhance the predictive accuracy and applicability of these systems, ensuring that organizations remain resilient in the face of new and emerging fraud tactics.

The Impact of AI on Real-Time Payments (RTP) for Small and Medium-Scale Enterprises' Performance in the United States of America

This study evaluated the impact of Ai on real time payment (RTP) for small and medium scale enterprises performance in United States of America with the aim of answering the research questions on how AI technologies adopted by US SMEs have facilitated access of payment rate, the extent at which AI technology impact the performance of US SMEs using a literature review approach. Findings from the analysed data confirmed that the rate of digital payments transactions in the US is growing on a fast rate which was also confirmed by recent empirical studies conducted after 2020 period stressing that the adoption of AI technologies by U.S. SMEs significantly impacts their access to payment rates particularly during the periods after the pandemic. This study also revealed that the impact of AI on the performance of SMEs in the United State appears to be unstable with the sampled periods of 2019 to 2024 with larger percentage of the sampled respondents in 2024 indicating that their business was in a favourable condition. On the final note, the findings revealed that the integration of artificial intelligence (AI) technology significantly enhances risk management for small and medium-sized enterprises (SMEs) in the US majorly in terms of influencing informed decision making, operational efficiency and response to market fluctuations. This study thereby recommended that SMEs in US should keep adopting AI technology for transaction processing, decision making, market forecast, fraud detection, compliance processes, credit risk management, data quality monitoring and operational resilience.

The Role of AI in Improving Customer Service, Fraud Detection, and Risk Management in Banking

The Role of AI in Improving Customer Service, Fraud Detection, and Risk Management in Banking

Digital Twin and IoT-Enabled Online Learning Model for Real- Time Monitoring and Control of Fraudulent Transaction in the Banking industry

Fraudulent transactions have long been a challenge in the banking industry, causing significant financial losses and operational burdens. Traditional fraud detection systems often struggle to adapt and respond in real-time to the evolving tactics of fraud. This study aims to develop a digital twin and IoT-enabled online learning model for real-time monitoring and control of fraudulent transactions in banking. The proposed system integrates digital twin technology and IoT sensors to create a virtual replica of transaction environments, enabling continuous learning and adaptation using an online learning model. Performance metrics such as detection speed, prediction accuracy, precision, recall, and F1 score were used to evaluate the system. The system was tested using a dataset of banking transactions, including legitimate and fraudulent activities. Key results include detecting fraudulent transactions 40% faster than traditional methods, reducing detection time from 5 minutes to 3 minutes. The model achieved an accuracy of 92%, an 8.24% improvement over traditional fraud detection systems. The false positive rate was reduced by 28%, meaning fewer legitimate transactions were wrongly flagged as fraudulent. Precision increased by 5.95%, reaching 89%, and recall improved by 8.75%, reaching 87%. This led to a 7.32% increase in the F1 score, reaching 88%. The system offers enhanced real-time fraud detection capabilities, reducing false positives and improving overall security and operational efficiency in the banking industry.

Evaluating the impact of risk management and risk-based internal audit on fraud detection in local governments

One of the leading indicators for improving fraud detection capability is the evaluation of the implementation of risk management and risk-based internal audit and information technology systems. This study aims to evaluate how risk management and risk-based internal audits influence fraud detection capabilities in local government when integrated with information technology systems. SPSS 26 was utilized for data analysis. The paper uses a quantitative approach, collecting primary data with questionnaires distributed among 200 auditors and 70 supervisors across four districts in West Java. A purposive sampling approach based on self-selection was used. The findings show that the ability to detect fraud is significantly and positively influenced by the implementation of a risk-based internal audit (sig 0.000 < 0.05) and risk management process (sig 0.000 < 0.05). On the other hand, the risk management framework (sig 0.107 > 0.05) has a negative and insignificant effect on improving fraud detection capability. In addition, the relationships between the risk management process (sig 0.006 < 0.05) and fraud detection capability were found to be moderated by information technology systems. However, information technology systems are unable to moderate the relationship between risk-based internal audit (sig 0.563 > 0.05) and risk management framework (sig 0.115 > 0.05) on fraud detection capability. Therefore, risk management and risk-based internal audits are able to detect fraud, and information technology systems can strengthen the risk management process with the ability to detect fraud. AcknowledgmentThe authors would like to thank the University of North Sumatra, especially the Research Institute, for its support and the Ministry of Education and Research through the Directorate of Research, Technology, and Community Service program for providing intellectual assistance and funding for this project in the PMDSU grant (number: 91/UN5.4.10.S/PPM/KP-DRTPM/2024).

Strengthening Fraud Control Plan For Investigative Audit And Probity Audit In Fraud Detection

The high number of corruption cases in local governments in Indonesia demands increased government attention to fraud cases. Opportunity for fraud can start from the planning stage to follow-up so that appropriate preventive and repressive handling efforts are needed. The Financial and Development Supervisory Agency has developed a fraud control plan and probity audit guidelines that are expected to be a solution to eradicate fraud in local governments. This study aims to analyse the effect of implementing investigative and probity audits on strengthening the fraud control plan in detecting fraud by auditors of the Financial and Development Supervision Agency of South Sulawesi and West Sulawesi. This study used quantitative with multiple linear analysis with Smart PLS 3.0 Software. Results found that investigative and probity audits positively affect fraud detection. Meanwhile, the fraud control plan does not strengthen the relationship between investigative and probity audits to fraud detection.

Analysis of the Role of Government Internal Supervisory Apparatus (APIP) in the Prevention and Detection of BOS Fund Fraud (Case Study of the Regional Inspectorate of North Sulawesi Province)

Analysis of the Role of Government Internal Supervisory Apparatus (APIP) in the Prevention and Detection of BOS Fund Fraud (Case Study of the Regional Inspectorate of North Sulawesi Province)

Machine Learning for Improved Detection and Prevention of Credit Card Fraud

Using machine learning to identify instances of credit card fraud is the primary goal of the research. In order to accomplish this, we will research and assess four distinct classification models: Decision Tree, Logistic Regression, K-Nearest Neighbours (KNN), and Support Vector Classifier (SVC). Included in the Kaggle dataset's "Time," "Amount," and "Class" sections are transaction data points that represent the likelihood of fraud. Disparities in class distribution are a big problem with this dataset, even though 99.83% of the data comes from legitimate transactions. Disparity like this has the potential to lead to biassed model training. We resolved the issue by implementing preprocessing techniques such as feature scaling and resampling. F1-Score, recall, accuracy, and precision are the measures that we use to assess the models. With scores ranging from 93% to 94%, the data demonstrate that all models are incredibly accurate. Having said that, Logistic Regression lacks precision. All things considered, Decision Tree, KNN, and SVC perform very well. The proposed model's accuracy peaked at 94%. As this study demonstrates, thorough evaluation criteria are necessary for finding the optimal model for fraud detection.

Fortifying financial integrity: Advanced fraud detection techniques for business security

Fortifying financial integrity: Advanced fraud detection techniques for business security

Detecting pyramid scheme activity with Google trends data

ABSTRACT This article explores the relationship between pyramid scheme participation and internet search activity, using a case study of a shuttered pyramid scheme in the United States. Comparing results against the Bass diffusion model, we estimate the relationship between monthly pyramid scheme uptake at the state level and the search frequency of key terms in that state (e.g. the scheme name). Using monthly data from 2004 to 2013, we find evidence that Google Trends data can be an effective complement to other fraud detection methods at the state level. This tool is especially useful in situations where consumer complaints are rare, and it is difficult to detect or measure the level of scheme activity.

Setting new benchmarks for combating financial crimes and ensuring the safety and security of America's digital financial landscape

The increasing digitalization of financial services in the United States has introduced significant challenges in combating financial crimes, including fraud, money laundering, and cybercrimes. As digital transactions become more pervasive, so too do the opportunities for illicit activities that exploit the vulnerabilities of these systems. This research seeks to establish new benchmarks for combating financial crimes and ensuring the security of America's digital financial landscape. By leveraging advanced technologies such as Artificial Intelligence (AI), Machine Learning (ML), and blockchain, this study explores innovative approaches to enhancing fraud detection, improving transparency, and reducing the risk of money laundering. A mixed-methods approach was employed, combining qualitative analysis of existing regulatory frameworks with quantitative case studies to assess the effectiveness of these technologies in real-world applications. The results indicate that AI and ML significantly enhance financial institutions' ability to detect fraudulent activities in real-time, reducing false positives and allowing for more efficient resource allocation. Furthermore, blockchain technology improved financial transactions' traceability, enhancing financial systems' transparency and accountability. The study concludes with recommendations for policy and practice, emphasizing the need for adaptive regulatory frameworks, increased investment in advanced technologies, and more vital collaboration between the public and private sectors. These findings suggest that a proactive approach, integrating technological innovation with strategic policy measures, is crucial for safeguarding America's financial infrastructure against emerging threats in the digital era.

An Ensemble Method for the Fraud Detection in Transactions

In today's world, bank fraud has become one of the significant threats to the financial stability and security of clients of financial institutions. The development of technologies, in particular in the field of machine learning, opens up wide opportunities for building effective systems for detecting and preventing fraud in the banking sector [1, 2]. Detecting fraudulent transactions is an important task that requires thoughtful and technological solutions. One of these methods is the use of machine learning approaches and methods. This paper proposes the use of an ensemble method that combines several machine learning models at once. This approach will reduce the probability of false positives and increase classification accuracy. In addition, for the optimal operation of the model, preprocessing of the data will be carried out, in particular, their normalization, balancing of classes, as well as the selection of features. During the research, it is important not only to achieve high accuracy, but also to reduce as much as possible the number of fraudulent transactions that will be mistakenly classified as normal [3]. This is related to the business requirements of the banking sector, as each such transaction causes losses to the system's reputation, as well as direct financial losses. Within the framework of the study, it is substantiated that the use of this approach gives better classification results than single models due to the compensation of the shortcomings of each of them. The choice of this approach is also due to high practicality, compatibility with financial systems, as well as ease of integration. This paper analyzes the proposed model, its advantages and disadvantages in comparison with analogues. The ensemble method helps to combine the advantages of simple models and reduce the impact of their shortcomings on the final result. In general, the choice of software should depend on the technical requirements of the project and to obtain better results, different models and approaches should be analyzed.