부산대학교 도서관

With the continuous improvement of the medical insurance system and the continuous expansion of medical insurance coverage, the normal operation of the medical insurance fund has been closely related to the vital interests of the people. Medical fraud detection methods can effectively reduce the loss of medical insurance funds and improve medical quality. This paper proposes an effective fraud identification method to detect abnormal expenses in the medical insurance reimbursement process. Experiments on real medical insurance data prove that the method has good fraud detection accuracy. At the same time, as the amount of data increases, the performance advantages of our proposed method are more obvious.