<![CDATA[This study aims to analyze the contribution of Big Data in enhancing fraud detection effectiveness by utilizing data characteristics—volume, velocity, and variety—to identify suspicious activities with greater precision. Employing a Systematic Literature Review (SLR) method, this research synthesizes findings on techniques such as machine learning, data mining, and predictive analytics applied to detecting fraud patterns and compares their performance with conventional approaches. The results reveal that Big Data–based systems demonstrate superior accuracy, reduced false positive and false negative rates, and faster response times compared to traditional methods. The integration of Big Data with Internal Control over Financial Reporting (ICoFR) further strengthens internal control structures and improves financial reporting transparency through automated audit trail tracking. Additionally, this study identifies several challenges faced by organizations, including technical limitations, regulatory constraints, and human resource competency gaps in implementing technology-based fraud detection systems. Based on these insights, the study delivers strategic recommendations to optimize policies, technological infrastructures, and workforce capabilities to support more adaptive and responsive anti-fraud mechanisms in addressing contemporary fraud risks.]]>
Copyrights © 2026
