An Enhanced Approach for Workmen’s Compensation Insurance Fraud Detection Based on Fuzzy Rule-Based System

In Workmen’s Compensation insurance, fraud detection (FD) remains a significant challenge due to claims' inherent uncertainty and complexity. To address this, we propose an enhanced approach based on a fuzzy rule system (FRS) for FD. The FRS is designed to handle ambiguous and imprecise data, making it effective for identifying fraudulent patterns in insurance claims. Unlike traditional methods, the fuzzy system utilizes human-like reasoning by applying flexible rules to assess the likelihood of fraud under uncertain conditions. By modeling the decision-making process with fuzzy logic, the system allows for a detailed evaluation of claims, accommodating the gray areas that often exist in FD. This approach enables accurate and adaptive FD, reducing false positives and enhancing the precision of fraud identification. In imbalanced FD scenarios, the system achieves strong performance, such as an F1-score of 0.82 and MCC of 0.75, demonstrating its capability to correctly identify rare fraudulent cases despite class imbalance.