Forensic Accounting and Fraud Detection Emerging Trends and Techniques

Abstract

Background: Forensic accounting has transformed greatly by incorporating advanced technologies, making it essential for uncovering and stopping fraud. This study explores how artificial intelligence (AI), blockchain, and data analytics can improve forensic accounting techniques. Objective: This study is focused on assessing how well new forensic accounting technologies enhance the efficiency of fraud detection and comparing it to previous studies. Methods: A variety of techniques, including regression analysis, Beneish M-Score, and Benford's Law, were used in a comprehensive methodology to assess the effectiveness of forensic accounting on 100 companies. Furthermore, the effect of employing blockchain on transparency and detecting fraud was examined for 50 companies. Results: The results of the regression analysis show that both data analytics (β=0.35) and AI (β=0.30) have a substantial positive impact on improving fraud detection effectiveness. Businesses that have a large number of transactions and utilize blockchain technology show better transparency and traceability, leading to better detection of fraud. The Beneish M-Score detected multiple companies that may be manipulating earnings, supporting previous research results. Conclusion: The utilization of advanced technologies like AI, blockchain, and data analytics significantly enhances the efficiency of forensic accounting in detecting and preventing fraud. Nevertheless, a significant amount of funds must be invested in infrastructure and training to achieve successful implementation. Future studies should investigate how these technologies can be applied more effectively in forensic accounting by examining their scalability and long-term effects in different fields and areas.