Risk scoring model construction method, device, storage medium and terminal

Abstract

The present invention provides a risk scoring model construction method. The construction method includes the following steps that: a blacklist sample library and a whitelist sample library are constructed according to preset account data, wherein the blacklist sample library includes abnormal accounts, and the whitelist sample library includes normal accounts; cluster training is performed on theabnormal accounts in the blacklist sample library and the normal accounts in the whitelist sample library on the basis of a gradient boosting decision tree (GBDT) algorithm, and abnormal account classification features are screened out; the abnormal account classification features are trained on the basis of a random forest (RF) algorithm, and a contribution degree corresponding to each abnormalaccount classification feature is obtained; and a risk scoring model is constructed according to the abnormal account classification features and the contribution degrees corresponding to the abnormalaccount classification features, and the risk scoring model is used for identifying the abnormal accounts. The risk scoring model constructed by the method of the invention improves the timeliness ofclearing the abnormal accounts, reduces noise interferences caused by the abnormal accounts, and improves the calculation precision of many indicators of APPs.

Description

technical field [0001] The invention belongs to the technical field of communication, and in particular relates to a method, device, storage medium and terminal for constructing a risk scoring model. Background technique [0002] At present, there are a large number of abnormal false registered users in the life insurance APP, and these false registered users have behaviors such as swiping activity and swiping activities. The APP activity rate is the ratio of the number of times the APP is logged on to the total number of users, and the conversion rate is the ratio of the number of customers acquired to the number of users who purchase products. Existing abnormal account identification methods are passive identification mechanisms such as post-event analysis, and the timeliness and accuracy of clearing abnormal accounts are low, which leads to great noise interference in the evaluation and improvement of APP activity rate and conversion rate by false registered users. Reduc...

AI Technical Summary

Problems solved by technology

Existing abnormal account identification methods are passive identification mechanisms such as post-event analysis, and the timeliness and accuracy of clearing abnormal accounts are low, which leads to great noise interference in the evaluation and improvement of APP activity rate and conversion rate by false registered users. Reduced the calculation accuracy of many indicators in the APP

In addition, due to the stimulation of the demand of false registered users, criminals also use the inherent loopholes in the APP to complete the registration of abnormal accounts, and derive a variety of abnormal user registration versions, which poses a greater security risk.

Images