Service prediction model creation method and device and computer readable storage medium

Abstract

According to the service prediction model creation method and device and the computer readable storage medium provided by the invention, firstly, a plurality of auxiliary data sets similar to a target data set are found; then, sampling is carried out from the multiple auxiliary data sets to obtain a sample data set, and a service state model is obtained through training of the sample data set; then, obtaining a default probability through the service state model, and determining a modeling data set based on the default probability; then, based on the target data set and the modeling data set, weight parameters are determined; and finally, establishing a service prediction model according to the modeling data set and the weight parameters. According to the scheme, the auxiliary dataset similar to the target dataset is used, the modeling dataset is screened out in a quantification mode, and the sample weight in the modeling dataset is adjusted, so that the samples in the modeling dataset are closer to samples of services corresponding to the to-be-created service prediction model, and the service prediction efficiency is improved. And the created service prediction model can have higher prediction capability and stability.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, relates to a method, device and computer-readable storage medium for creating a service forecast model. Background technique [0002] During model development, a large amount of sample data is generally required. At the beginning stage of a business, there will be few sample data (business objects and business status labels), etc., and it is impossible to develop models based on the existing current sample data. , or the developed model's predictive ability is biased and the effect is unstable. Contents of the invention [0003] In order to at least overcome the above-mentioned deficiencies in the prior art, the purpose of the present application is to provide a business forecasting model creation method, device and computer-readable storage medium for solving the above-mentioned technical problems. [0004] In the first aspect, the embodiment of th...

AI Technical Summary

Problems solved by technology

[0002] During model development, a large amount of sample data is generally required. At the beginning stage of a business, there will be few sample data (business objects and business status labels), etc., and it is impossible to develop models based on the existing current sample data. , or the developed model’s predictive ability is biased and the effect is unstable

Images