A Novel Multi-view Bi-clustering method for identifying abnormal Co-occurrence medical visit behaviors.

Abnormal co-occurrence medical visit behavior is a form of medical insurance fraud. Specifically, an organized gang of fraudsters hold multiple medical insurance cards and purchase similar drugs frequently at the same time and the same location in order to siphon off medical insurance funds. Conventional identification methods to identify such behaviors rely mainly on manual auditing, making it difficult to satisfy the needs of identifying the small number of fraudulent behaviors in the large-scale medical data. On the other hand, the existing single-view bi-clustering algorithms only consider the features of the time-location dimension while neglecting the similarities in prescriptions and neglecting the fact that fraudsters may belong to multiple gangs. Therefore, in this paper, we present a multi-view bi-clustering method for identifying abnormal co-occurrence medical visit behavioral patterns, which performs cluster analysis simultaneously on the large-scale, complex and diverse visiting record dimension and prescription dimension to identify bi-clusters with similar time-location features. The proposed method constructs a matrix view of patients and visit records as well as a matrix view of patients and prescriptions, while decomposing multiple data matrices into sparse row and column vectors to obtain a consistent patient population across views. Subsequently the proposed method identifies the corresponding abnormal co-occurrence medical visit behavior and may greatly facilitate the safe operations and the sustainability of medical insurance funds. The experimental results show that our proposed method leads to more efficient and more accurate identifications of abnormal co-occurrence medical visit behavior, demonstrating its high efficiency and effectiveness.

A Survey on Federated Recommendation Systems.

Federated learning has recently been applied to recommendation systems to protect user privacy. In federated learning settings, recommendation systems can train recommendation models by collecting the intermediate parameters instead of the real user data, which greatly enhances user privacy. In addition, federated recommendation systems (FedRSs) can cooperate with other data platforms to improve recommendation performance while meeting the regulation and privacy constraints. However, FedRSs face many new challenges such as privacy, security, heterogeneity, and communication costs. While significant research has been conducted in these areas, gaps in the surveying literature still exist. In this article, we: 1) summarize some common privacy mechanisms used in FedRSs and discuss the advantages and limitations of each mechanism; 2) review several novel attacks and defenses against security; 3) summarize some approaches to address heterogeneity and communication costs problems; 4) introduce some realistic applications and public benchmark datasets for FedRSs; and 5) present some prospective research directions in the future. This article can guide researchers and practitioners understand the research progress in these areas.