Insurance applicant user portrait mining method based on big data

Abstract

The invention discloses an insurance applicant user portrait mining method based on big data. The method comprises the following steps: governing data of each dimension in an existing database of an insurance company according to an insurance industry association standard to enable the data to accord with an industry standard and a company standard, and performing data fusion through an identity card number or an insurance number of a user to form a unified data center; acquiring data of an authorized access system of an insurance applicant, and performing data fusion on the identity card number of the insurance applicant and the data of the data center to form insurance applicant data; dividing the insurance applicant data into three levels of label systems; according to the constructed difficulty degree and the three-level label system, creating a priority label system, and continuously refining the data of the insurance applicant into data of each dimension through the priority label system; performing data analysis and mining on the insurance applicant data in the priority label system by adopting Spark Mllib; and generating a potential insurance applicant user portrait. According to the invention, the user portrait of a potential insurance applicant can be accurately and effectively constructed.

Description

technical field [0001] The present invention relates to the technical field of big data, in particular to a method for mining policyholder user portraits based on big data. Background technique [0002] Due to the development of the Internet and mobile technology, various insurance sales websites and mobile APP software have become new premium growth points for insurance companies. In this case, it is more difficult to verify the authenticity of materials, the information asymmetry is more prominent, the risk of opportunistic fraud increases, and the risk of accidents in different places increases. Higher requirements are placed on the underwriting and claims work, which is prone to gaps in the connection of insurance service processes. In the traditional insurance sales process, sales staff communicate with customers face to face, and there is a process of understanding customers and verification. However, the development of the Internet + mobile network has basically eli...

AI Technical Summary

Problems solved by technology

However, the development of Internet + mobile network makes this process basically disappear, and the nuclear insurance department loses a natural barrier, which increases the difficulty of risk control

Images