Using PCA to Improve the Detection of Medical Insurance Fraud in SOFM Neural Networks

Abstract

In view of the inefficiency and difficulty of detection in the traditional methods of abnormal detection of medical insurance fraud in patients, this paper combines data mining technology to realize the algorithm suitable for large-scale medical insurance data mining, and establishes effective anomaly feature extraction. model. The principal component analysis (PCA) method is used to reduce the dimension of the feature data, and the abnormal medical insurance information is analyzed, identified and processed. Then, the self-organizing feature map (SOFM) neural network is established to process the medical insurance fraud behavior detection. The test results show that the method can effectively extract the characteristics of medical insurance fraud behavior and can be effectively used for medical insurance abnormality detection.