Model training and business risk control method and device

Abstract

The invention discloses a model training and business risk control method and device. In the specification, a business platform determines each basic feature and a plurality of additional features asrisk control features according to acquired historical first business data and user attribute data of a user, and then determines a risk control data interval corresponding to the risk control featurefor each risk control feature; The platform inputs the feature data, which is determined from the historical first business data and the user attribute data of the user and is located in the risk control data interval corresponding to each risk control feature, into a risk control model to be trained, acquires a risk control model by training, and carries out business risk control on a second business by using the trained risk control model. Thus, in the embodiment of the specification, the risk control model obtained by training can be used for performing business risk control on the insurance business as second business, so that auditing workload of workers is reduced, and business execution efficiency is improved.

Description

technical field [0001] This specification relates to the field of Internet technology, and in particular to a method and device for model training and business risk control. Background technique [0002] With the development of social economy and the improvement of people's living standards, the insurance business is getting more and more attention from the public. In the past, when customers purchased insurance offline, insurance companies usually used manual verification to review the health status of the insured customer to determine whether the insured customer met the insurance conditions. [0003] Now, online insurance business is rapidly expanding due to the convenience of executing insurance business online. At present, insurance companies still use manual verification to check the health status of insured customers. This not only greatly increases the workload of the salesperson, but also reduces the operating efficiency. Contents of the invention [0004] This ...

AI Technical Summary

Problems solved by technology

At present, insurance companies still use manual verification to check the health status of insured customers, which not only greatly increases the workload of salespersons, but also reduces operating efficiency.

Images