<![CDATA[This systematic literature review examines the application of machine learning (ML) techniques in fraud detection within the auditing domain, synthesizing findings from peer-reviewed studies published between 2019 and 2024. Following the PRISMA 2020 guidelines, this review analyzed 85 articles from Scopus, Web of Science, IEEE Xplore, and Google Scholar databases. The Kitchenham methodology was employed to ensure rigorous screening, extraction, and synthesis of relevant literature. The review reveals that ensemble methods, particularly Random Forest and XGBoost, demonstrate superior performance in fraud detection tasks. Deep learning architectures, including Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, show promising results for complex fraud patterns. Key challenges identified include imbalanced datasets, model interpretability, and regulatory compliance. The emergence of Explainable AI (XAI) techniques, such as SHAP and LIME, addresses transparency concerns in audit applications. This review provides a comprehensive synthesis of ML applications in fraud detection specifically within the auditing context, offering a research agenda for future investigations and practical implications for audit practitioners and regulators.]]>
Copyrights © 2026
