The role of artificial intelligence in enhancing audit quality and fraud detection: Literature analysis, empirical evidence, and implementation requirements

The role of artificial intelligence in enhancing audit quality and fraud detection: Literature analysis, empirical evidence, and implementation requirements

Ali Rezaei Rad1

1) Lecturer, Islamic Azad University, Yasuj Branch

IOI Code : ABKH-ABHHFF
Publication : 4th International Conference on Applied Researches in Humanities, Economics, Management & Accounting(icrhema.com)
Abstract :
    In recent years, digital transformation has altered the nature of many professional processes, and the auditing profession is no exception. The expansion of big data, increasing transaction complexity, growing stakeholder expectations for transparent financial reporting, and the need for timely detection of anomalies and fraud have made artificial intelligence a major driver of change in auditing. This study examines the role of artificial intelligence in enhancing audit quality and improving fraud detection capability by drawing on theoretical literature, international empirical evidence, and selected domestic studies. The research adopts a descriptive-analytical approach based on a systematic review of credible domestic and international sources in auditing, accounting, and intelligent technologies. The findings suggest that artificial intelligence improves audit quality through three main channels: expanding audit coverage, strengthening anomaly detection, and enhancing the speed and accuracy of evidence analysis. Empirical evidence indicates that investment in artificial intelligence is associated with a lower likelihood of financial statement restatements and reduced audit costs. Domestic studies also show that machine learning algorithms have demonstrated promising performance in fraud prediction and detection. However, artificial intelligence is not a complete substitute for auditors’ professional judgment; rather, it serves as a complementary tool to strengthen professional capability. Key challenges include model interpretability, algorithmic bias, data confidentiality, implementation costs, organizational resistance, and limited digital skills. The study concludes that audit firms, universities, and regulatory bodies should adopt a gradual and governance-oriented approach to support the responsible and effective use of artificial intelligence in auditing. Keywords: artificial intelligence, audit quality, fraud detection, continuous auditing, machine learning, financial reporting

Keywords : artificial intelligence audit quality fraud detection continuous auditing machine learning financial reporting