User information classification method and device

Abstract

The embodiment of the invention provides a user information classification method and device, and the method comprises the steps: carrying out the model training of a first training feature variable with a label, obtaining a first user information classification model, carrying out the clustering of a second training feature variable in an intermediate state through an unsupervised algorithm, andthen determining the label; therefore, the limitation of artificial identification is broadened, and a second user information classification model is further obtained after model training is carriedout by using the second training feature variable after label determination. And then user information classification is performed on the original first training feature variable based on the second user information classification model and then training of the third user information classification model is performed so that the data utilization rate can be enhanced by utilizing the full-amount intermediate sample data, and the data utilization rate can be enhanced due to increase of the data utilization rate. The modeling effect and the user information classification effect of the original first user information classification model are also improved, and the multiple user information classification models are generated, so that the method is more convenient and flexible in actual use.

Description

technical field [0001] The present application relates to the technical field of computer risk control, in particular, to a user information classification method and device. Background technique [0002] In the existing risk control business scenario, when determining the definition of the label of the modeling sample, the rolling rate analysis is generally used to obtain the definition of different labels and combined with business experience to determine the label of the modeling sample, and then based on the definition of this label to Perform wind control modeling. Among them, the number of samples in the intermediate state generally enters the modeling samples according to a certain proportion of the total modeling samples or directly deletes the samples in the intermediate state for risk control modeling. [0003] However, the inventor found that according to the above scheme, after defining the labels of the samples in the risk control modeling, there will be some s...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found that according to the above scheme, after defining the labels of the samples in the risk control modeling, there will be some sample data in an intermediate state, and these intermediate modeling samples cannot be determined during the modeling process. Whether it is directly deleting these sample data for modeling or selecting some intermediate state samples to enter the model, it will face the problem that the modeling samples will become smaller to varying degrees, which will weaken the learning effect of the model, especially when the modeling samples are limited. This problem is particularly prominent in the case of

Images