Unlock instant, AI-driven research and patent intelligence for your innovation.

User characteristic classification method for user credit model, user credit evaluation method and device

A technology of user characteristics and characteristic classification, which is applied in the field of data processing and can solve problems such as large deviations in actual user credit

Active Publication Date: 2017-08-01
ALIBABA GRP HLDG LTD
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a user feature classification method of a user credit model, a user credit evaluation method and device, which are used to solve the problem in the prior art that the estimated user credit usually deviates greatly from the actual

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • User characteristic classification method for user credit model, user credit evaluation method and device
  • User characteristic classification method for user credit model, user credit evaluation method and device
  • User characteristic classification method for user credit model, user credit evaluation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Embodiment 1 provides a method for classifying user characteristics of a user credit model, which is used to classify user characteristics in the user credit model, thereby laying a foundation for accurate evaluation of user credit. The specific flow chart of the method is shown in figure 1 shown, including the following steps:

[0061] Step S11: Extracting the characteristics of each user in the user credit model.

[0062] Here, the user credit model means that the model is used to evaluate the user's personal credit. It should be noted that in practical applications, the selected user characteristics may also be different for different user credit models.

[0063] In addition, user characteristics are the abstract results of user attributes related to user credit, and these user attributes may include age, gender, income, and so on. Usually in practical applications, when building a user credit model, user features must first be processed through feature engineering...

Embodiment 2

[0077] Embodiment 2 provides a user credit evaluation method of a user credit model, in which each user feature in the user credit model is classified into a specified user feature set and a non-specified user feature set according to the method of embodiment 1, and the non-specified user feature set The designated user characteristic set contains at least one non-designated user characteristic. The specific flow chart of the method is shown in figure 2 shown, including the following steps:

[0078] Step S21: Receive user characteristic data of each user characteristic.

[0079] Here, each user feature refers to each user feature corresponding to the user credit model. For example, the user credit model is constructed by three user characteristics, which are user age, marital status and salary income, respectively, and the user characteristics are specifically the three user characteristics of user age, marital status and salary income.

[0080] In practical applications, ...

Embodiment 3

[0100] Embodiment 1 and Embodiment 2 classify user characteristics through user credit model, and then process user characteristic data, so as to evaluate user credit according to the output value after processing. For ease of understanding, the embodiment of the present application also provides a user credit evaluation method that specifically implements the user credit model in an actual application scenario, and the user credit model may also be described here first.

[0101] The user credit model includes a linear processing module and a nonlinear processing module, the linear processing module is used to linearly map the user characteristic data of each designated user characteristic in the designated user characteristic set, and the nonlinear processing module is used to Non-linear processing is performed on the user characteristic data of each non-designated user characteristic in the non-designated user characteristic set.

[0102] In practical applications, in order ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a user characteristic classification method for a user credit model, a user credit evaluation method and a device. the user credit evaluation method comprises steps: user characteristic data of each user characteristic are received; user characteristic data of each non-specified user characteristic in a non-specified user characteristic set are subjected to nonlinear processing, and a first numerical value is determined according to a nonlinear processing result; user characteristic data of each specified user characteristic in a specified user characteristic set are subjected to linear mapping, and a second numerical value is determined according to a linear mapping result; through the first numerical value and the second numerical value, the output value of the user credit model is determined; and the user credit is evaluated according to the output value. Thus, the problem that in the prior art, all characteristic data are processed in the same mode, and thus, the user credit evaluated and obtained according to the processing result greatly deviates from the reality can be solved.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a method for classifying user characteristics of a user credit model, a method and a device for evaluating user credit. Background technique [0002] With the vigorous development of the Internet, machine learning (Machine Learning, ML) technology, as a new technology, has attracted more and more attention. Machine learning technology is usually used to predict user behavior, which can be realized through various user models in practical applications. For example, the user credit model can be used to process the user characteristic data related to the user's personal credit, and predict the user's personal credit consumption and other behaviors according to the processing results. [0003] In the prior art, when the user credit model is used to process feature data, the result of data processing is obtained by weighting and summing each feature data of the user...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/2453
Inventor 席炎余舟华杨强鹏漆远褚崴王晓光李文鹏施兴俞吴杰
Owner ALIBABA GRP HLDG LTD