Risk Analysis and Countermeasures of Social Medical Insurance Based on Random Matrix Theory and Data Mining

• Published in: Mathematical problems in engineering Vol. 2022; pp. 1 - 11
• Main Author: Chen, Cuixia
• Format: Journal Article
• Language: English
• Published: New York Hindawi 18.07.2022; John Wiley & Sons, Inc
• Subjects: Algorithms; Associations; Audits; Business administration; Construction; Correlation analysis; Data mining; Data warehouses; Decision support systems; Health insurance; Insurance; Mathematical problems; Matrix theory; Online analytical processing; Quality management; Risk analysis; Risk assessment; Social security; Supervision; Trends
• ISSN: 1024-123X; 1026-7077; 1563-5147; 1563-5147
• DOI: 10.1155/2022/6429510

Accelerating the reform of social medical insurance risk analysis is an urgent need to establish a complete social medical insurance system. Based on random matrix theory and data mining technology, this study constructs a social medical insurance risk analysis model. After determining the subject of the data warehouse and the relevant information of each subject, it starts to build a random matrix data warehouse, and solves the social medical insurance risk through the data fact table and dimension quantitative indicators. In the simulation process, the model uses the Oracle Warehouse Builder (OWB) software to create the data warehouse, and systematically analyzes and studies the construction process of each table; when creating the server through data mining, we run the repository as an administrator program to create data mining workspace, including creating OWB username and password. The experimental results show that after analyzing related technologies such as data warehouse, OLAP, and data mining, the accuracy rate of abnormality is 79.0%, and the recall rate is 85.8%. After using random matrix sampling technology to balance the dataset, the algorithm effect accuracy rate reaches 89.3%, which can effectively provide professional help for the social security fund supervision department and the medical insurance business management department.