<![CDATA[This study aims to evaluate the impact of digital technologies on detecting financial statement fraud through the application of machine learning, deep learning, artificial intelligence (AI), big data analytics, and blockchain. In addition, the study seeks to identify existing knowledge gaps to guide future academic research. The methodology employed is a Systematic Literature Review (SLR), focusing on Scopus-indexed journal articles published between 2020 and 2025. Using predefined keywords derived from relevant literature, a total of 27 articles were selected as the primary sources for analysis. The SLR approach enabled a structured evaluation of key aspects, including research themes, findings, methodologies, recommendations, and limitations within each study. The results indicate that machine learning, deep learning, and data mining have a positive influence on enhancing the effectiveness of financial fraud detection. These technologies support auditors by improving accuracy in identifying potentially fraudulent activities. Their ability to uncover hidden patterns and complex relationships within large datasets allows for more effective detection of anomalies and fraud indicators. However, the review also reveals several strengths and weaknesses associated with the algorithms employed across existing studies. Based on these insights, the research provides recommendations for future work, such as developing more advanced detection algorithms and investigating the factors that hinder the adoption of digital technologies in financial fraud detection practices]]>
Copyrights © 2026
