ARTIFICIAL INTELLIGENCE IN FRAUD DETECTION: ARE TRADITIONAL AUDITING METHODS OUTDATED? (original) (raw)
Related papers
AI in Auditing: A Comprehensive Review of Applications, Benefits and Challenges
Shodh Sari-An International Multidisciplinary Journal
The rapid evolution of artificial intelligence (AI) technologies has brought about transformative changes in various industries, and the field of auditing is no exception. This research paper presents a comprehensive review of the integration of AI in auditing practices, highlighting its applications, benefits, and associated challenges. Auditing, a critical process for ensuring the accuracy and reliability of financial information, has traditionally been a labor-intensive and time-consuming endeavor. The emergence of AI technologies, such as machine learning, natural language processing, and data analytics, has revolutionized the way audits are conducted. AI-powered auditing tools offer advanced capabilities for data analysis, pattern recognition, anomaly detection, and risk assessment. These capabilities enhance the effectiveness and efficiency of audits by allowing auditors to focus on high-risk areas and perform more in-depth analysis. The paper explores various applications of ...
Deleted Journal, 2024
AI is anticipated to enhance competitive advantages for financial organisations by increasing efficiency through cost reduction and productivity improvement, as well as by enhancing the quality of services and goods provided to consumers. AI applications in finance have the potential to create or exacerbate financial and non-financial risks, which could result in consumer and investor protection concerns like biassed, unfair, or discriminatory results, along with challenges related to data management and usage. The AI model's lack of transparency may lead to pro-cyclicality and systemic risk in markets, posing issues for financial supervision and internal governance frameworks that may not be in line with a technology-neutral regulatory approach. The primary objective of this research is to explore the effectiveness of Artificial Intelligence in preventing financial misconduct. This study extensively examines sophisticated methods for combating financial fraud, specifically evaluating the efficacy of Machine Learning and Artificial Intelligence. When examining the assessment metrics, this study utilized various metrics like accuracy, precision, recall, F1 score, and the ROC-AUC. The study found that Deep Learning techniques such as "Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks /Long Short-Term Memory, and Auto encoders" achieved high precision and AUC-ROC scores in detecting financial fraud. Voting classifiers, stacking, random forests, and gradient boosting machines demonstrated durability and precision in the face of adversarial attacks, showcasing the strength of unity.
How Accounting Artificial Intelligence Can Prevent Fraud ? (Status and Research Opportunities)
2021
The implementation of information technology is crucial as a fraud prevention mechanism, the industrial revolution has triggered the optimization of information technology that increasingly resembles humans or what we call artificial intelligence. Human has limitations in the capacity of data storage and analysis of decision making. The purpose of this study was to provide a description of the results of research related to artificial intelligence and the role of artificial intelligence in preventing fraud. The research method of this research is qualitative by conducting a literature review based on the results of previous studies without any classification criteria for journal sources. The results showed that the majority of research in this study still used a qualitative approach and literature reviews, it was rare that research conducted in-depth analysis or detailed case studies related to the implementation of artificial intelligence. The results also show that the application...
THE FUTURE OF AUDITING IN THE AGE OF AI: HOW AUTOMATION IS RESHAPING THE AUDIT PROFESSIO
2019
The research aims to evaluate the impact of artificial intelligence (AI) and automation on the audit profession, focusing on improvements in efficiency, accuracy, and cost-effectiveness. A literature review methodology was employed, synthesizing insights from studies and industry reports on AI’s influence on auditing processes, ethical implications, and the evolving skill sets required for auditors. Key findings reveal that AI-powered methods achieve an 89% accuracy in fraud detection, outperforming traditional methods at 72%, and reduce false positives from 15% to 8% and false negatives from 13% to 3%. These findings underscore AI’s ability to minimize audit time, enhance fraud detection, and reduce operational costs. The study recommends ongoing auditor training in AI and data analytics, scalable AI tools for smaller firms, and stringent ethical and regulatory frameworks to guide AI use in auditing. Monitoring AI misclassification rates remains critical to sustaining effectiveness and precision in fraud detection. Key Words: Artificial Intelligence, Auditing, Automation, Fraud Detection, Regulatory Compliance
Fraud Detection Automation Through Data Analytics and Artificial Intelligence
Riset
This study aims to review the use of data analytics and artificial intelligence in fraud detection to support internal audits. This study employs a qualitative method with a scoping review approach. The research data comprised 24 online journal articles indexed by Scopus and Sinta, which were used as the basis for scoping reviews. The stages carried out in this study consisted of identifying research questions, using keywords, selecting literature, mapping the results of research data, and compiling a summary of research results. This study concludes that the fraud detection model based on data analytics and artificial intelligence has a high accuracy value in improving audit quality. This study indicates that the Indonesian Financial and Development Supervisory Agency needs to increase the use of technology, including data analytics and artificial intelligence, to detect fraud optimally.
International Journal of Multidisciplinary Research and Growth Evaluation, 2023
The detection and prevention of financial statement fraud is a critical concern for businesses, investors, and regulators. Traditional forensic accounting methods, such as financial statement audits and investigations, have been used to detect and investigate financial statement fraud, but they may not be sufficient to effectively address the evolving nature of fraud in today's complex business environment. The increasing use of technology in financial reporting and the abundance of data available have made it more challenging for forensic accountants to detect and investigate financial statement fraud. In light of these challenges, a paradigm shift in forensic accounting is needed to better detect and prevent financial statement fraud. This shift should focus on the use of advanced data analytics, machine learning, and continuous monitoring to identify and investigate fraudulent activity. Advanced data analytics can be used to identify unusual patterns and anomalies in financial data that may indicate fraudulent activity. Machine learning can be used to automatically detect and classify fraudulent transactions, and continuous monitoring can be used to identify and investigate fraudulent activity in real-time. By embracing this paradigm shift, forensic accountants can better detect and prevent financial statement fraud and improve the overall integrity of financial reporting.
UNCOVERING FRAUD IN THE DIGITAL ERA: INNOVATIVE TECHNIQUES FOR AUDITORS
2019
This research explores the effectiveness of data analytics, artificial intelligence (AI), and machine learning in enhancing fraud detection in digital financial ecosystems. A comprehensive literature review and secondary data analysis were employed, examining case studies and peer-reviewed articles. Major findings reveal that AI-driven fraud detection methods significantly improve accuracy, reaching up to 91% in 2019, surpassing traditional methods by 21% (p < 0.05). Regression analysis highlighted key fraud indicators, including transaction irregularities, demonstrating strong correlations with fraud likelihood (p < 0.01). The study concludes that AI integration in auditing not only increases detection precision but also reduces false positives by nearly 40% and auditing costs by 20%. Recommendations include ongoing auditor training in AI tools, standardized fraud indicators, and scalable AI solutions for diverse auditing environments.
Prospective assessment of ai technologies for fraud detection: A case study
1997
In September 1995, the Congressional O ce of Technology Assessment completed a study of the potential for AI technologies to detect money laundering by screening wire transfers. The study, conducted at the request of the Senate Permanent Subcommittee on Investigations, evaluates the technical and public policy implications of widespread use of AI technologies by the Federal government for fraud detection.
This study examines the impact of artificial intelligence (AI) and machine learning (ML) on professional roles within the context of financial reporting and auditing practices. Utilizing a quantitative approach, data were collected from 142 accountants in private businesses in Erbil through a structured questionnaire assessing perceptions on efficiency, accuracy, fraud detection, compliance, and professional impact. Statistical analyses, including multiple regression and correlation, were employed to determine the relationships between AI and ML integration and various professional outcomes. Contrary to expectations, the results revealed no significant impact of AI and ML on the perceived efficiency, accuracy, fraud detection capabilities, or compliance within the professional roles of accountants. These findings suggest a disconnect between the theoretical benefits of AI and ML technologies and their practical perceptions among professionals in the field. Recommendations include the need for enhanced training, incremental technology implementation, and improved governance structures to foster effective integration and utilization of AI and ML in financial practices. The study's implications are significant for organizations considering or currently implementing AI and ML technologies, highlighting the importance of addressing both technological and human factors to maximize the potential benefits of these innovations. Future research is encouraged to explore qualitative aspects of technology adoption and to conduct longitudinal studies to assess changes over time as professionals adapt to AI and ML tools. The limitations of the study, such as its geographical focus and cross-sectional design, suggest caution in generalizing the findings and point towards the need for broader, more diverse investigations. This research contributes to the ongoing discourse on the practical challenges of integrating advanced technologies in specialized professional domains, underscoring the need for a balanced approach that
International Journal for Multidisciplinary Research (IJFMR), 2024
AI in fraud detection and financial risk management has taken this role of prevention and combating fraud closely related to organizations and the losses they incur a next level. This paper aims to discuss the use of artificial intelligence models in the process of detecting frauds and preventing and reducing financial risks in such markets as banking, insurance, and fintech. Today, through machine learning algorithms, deep learning techniques, and data analysis, the AI improves the speed, accuracy and effectiveness of fraud detection. This paper discusses the current AI models and business use incorporating the success story and the business outcomes which has encountered sometime to have the best result. Furthermore, the paper examines other important issues of AI application management such as data security and liberation, and complete fairness control. Using examples as well as statistical data in this AI for business article, we show how corporations have managed to minimize their risks while lowering their expenses with the use of artificial intelligence technology. This research outlines ideas on how organizations can implement AI into fraud detection systems and what can be done in future to enhance the solutions. This paper adds to the emerging body of knowledge on AI's impact on finance and security, and demonstrates AI's ability to influence the future of the industry.