PROCESSING METHOD, APPARATUS AND DEVICE FOR RISK PREDICTION OF INSURANCE SERVICE

• Main Authors: WU, Longfeng, CHEN, Shiyi, ZHANG, Taiwei, CHEN, Yan, SHI, Qiuhui
• Format: Patent
• Language: Chinese; English; French
• Published: 21.11.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

A processing method, apparatus and device for risk prediction of an insurance service. A gradient boosting decision tree can be used in advance to construct a risk prediction model, the risk prediction model being able to be trained using risk-associated marked data associated with the insurance service. When the training of the risk prediction model satisfies a prediction requirement, the risk prediction model can be used as online risk prediction, performs insurance service risk prediction on a user to be predicted, and outputs a prediction result. Multidimensional nonlinear variables in the insurance service can be reasonably and effectively used, and the risk prediction model based on the nonlinear relationship of the gradient boosting decision tree can be well compatible with linear and nonlinear variables. Compared to the traditional linear model, the accuracy of the prediction result is significantly improved, the deficiency of the traditional linear model is effectively compensated for, and the servic