ARTIFICIAL INTELLIGENCE IN FORENSIC AUDITING: APPLICATIONS, CASE STUDIES, AND EMERGING CHALLENGES

The rapid advancement of Artificial Intelligence (AI) has significantly transformed forensic auditing practices. Traditional audit methods, which relied heavily on manual sampling and professional judgment, are increasingly being supplemented by AI-powered analytical tools capable of processing large-scale financial datasets (Bolton & Hand, 2002). This study examines the applications of AI in forensic auditing, including fraud detection, predictive analytics, anomaly identification, Natural Language Processing (NLP)-based document analysis, and blockchain investigation. Prior research demonstrates that machine learning models outperform traditional statistical and rule-based systems in detecting complex fraud patterns (Kirkos et al., 2007; Ngai et al., 2011; Perols, 2011). The study further evaluates real-world case contexts and discusses governance implications, ethical risks, and regulatory challenges associated with AI adoption. Findings indicate that AI-driven models significantly enhance fraud detection accuracy and reduce audit risk. However, concerns regarding algorithmic bias, data privacy, and model interpretability remain critical challenges in forensic auditing environments.   

Keywords: Artificial Intelligence, Forensic Auditing, Fraud Detection, Machine Learning, Predictive Analytics, Blockchain Forensics.