Posted: Aug 06, 2023
Corporate fraud represents a significant threat to global economic stability, with estimated annual losses exceeding $4 trillion worldwide. The increasing sophistication of fraudulent schemes necessitates continuous evolution in detection methodologies. Traditional forensic accounting techniques, while valuable, face limitations in addressing the complex, multi-faceted nature of modern corporate fraud. This research addresses the critical need for enhanced detection frameworks by developing and evaluating an integrated approach that combines established forensic accounting principles with advanced computational methods. The novelty of this research lies in its holistic framework that bridges the gap between traditional accounting expertise and cutting-edge computational analytics. While previous studies have explored either conventional forensic methods or standalone machine learning applications, our approach creates a synergistic detection system that leverages the strengths of both domains. This integration enables the identification of subtle fraud patterns that might remain undetected when using either approach independently.
Downloads: 6
Abstract Views: 2102
Rank: 47023