TITLE:
Integrating Machine Learning into Financial Forensics for Smarter Fraud Prevention
AUTHORS:
Wenxia Zheng, Yutong Tan, Bingying Jiang, Jiyuan Wang
KEYWORDS:
Machine Learning, Forensic Accounting, Fraud Detection, Financial Auditing, AI in Finance, Deep Learning
JOURNAL NAME:
Technology and Investment,
Vol.16 No.3,
July
3,
2025
ABSTRACT: This study explores the growing impact of machine learning (ML) on forensic accounting and fraud detection. As financial transactions and systems become increasingly complex and voluminous, traditional methods like manual audits and rule-based systems have struggled to keep up with the sophistication of modern fraud. Machine learning, a branch of artificial intelligence (AI), offers a transformative solution by automating the analysis of vast amounts of financial data, detecting anomalies, and uncovering hidden fraud patterns with high accuracy. This paper provides a comprehensive review of machine learning applications in forensic accounting, comparing them with traditional methods and examining various algorithms, such as supervised, unsupervised, and deep learning models, in fraud detection. It highlights the advantages of machine learning, including its scalability, adaptability, and ability to improve continuously over time. However, the paper also discusses the challenges of implementing ML in fraud detection systems, such as data quality issues, model transparency, ethical concerns, and legal constraints. Additionally, it addresses the future potential of ML in forensic accounting, including advancements in explainable AI (XAI), reinforcement learning, and hybrid models that integrate human expertise with machine learning-driven analysis. The findings underscore the transformative potential of machine learning in improving fraud detection while acknowledging the need for addressing its limitations to ensure broader adoption and effective implementation in the financial sector.