Optimization of Hospital Financial Anomaly Detection Model Based on Support Vector Machine

A hospital financial management anomaly detection framework that applies the D-S evidence fusion theory. Relying on the combination of machine learning, Support Vector Machine (SVM), and the D-S theory, this framework improves the detection accuracy and also enhances the robustness of the detection. This system is composed of parts such as the financial budget module, accounting module, reimbursement module and reporting module. The anomaly detection includes contents such as equipment identification, behavior monitoring and global analysis. The results obtained from the experiment show that the D-S model performs better than the support vector machine in content feature detection. This paper provides a reliable and efficient solution for hospital financial anomaly detection and risk prevention.