Risk evaluation method and system

A technology of risk assessment and risk assessment model, applied in instruments, complex mathematical operations, finance, etc., can solve problems such as insufficient mining and utilization of data, weak variables cannot be selected into models, etc., to achieve comprehensive risk assessment factors and improve risk assessment. Effects, model results Objective and accurate effects

Active Publication Date: 2017-08-08
TENCENT TECH (SHENZHEN) CO LTD
View PDF12 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The expert method can solve the problem that weak variables cannot be selected into the model. However, the expert method is a relatively subjective method that does not fully exploit and utilize the value of data.

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
  • Risk evaluation method and system
  • Risk evaluation method and system
  • Risk evaluation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Please refer to figure 1 , the first embodiment of the present invention provides a risk assessment method, which may include:

[0049] 110. Perform variable grouping according to the correlation between the data source and the target variable and / or the correlation between the data source and user information, to obtain at least one variable group of the first type and at least one variable group of the second type.

[0050] With the rapid development of the Internet, more and more information and data are available, and the data sources used in risk assessment methods are also becoming more and more extensive. Some of them have a stronger correlation with credit risk, while others have a weaker correlation. In this paper, the variables are first grouped according to the data source, and the variables of the same source are regarded as a variable group. For example, the three types of variables from payment, instant messaging, and social networking can be regarded as t...

Embodiment 2

[0107] (Embodiment 2) In order to better implement the above-mentioned solution of the embodiment of the present invention, related devices for coordinating the implementation of the above-mentioned solution are also provided below.

[0108] Please refer to Figure 4 , the embodiment of the present invention provides a risk assessment system 400, which may include:

[0109] A preprocessing module 410, configured to group variables according to the correlation between the data source and the target variable and / or the correlation between the data source and user information, to obtain at least one variable group of the first type and at least one variable group of the second type;

[0110] The first construction module 420 is configured to respectively construct a risk assessment model for the at least one second-type variable group, and respectively obtain the model results of the risk assessment model of each second-type variable group;

[0111] The variable combination modu...

Embodiment 3

[0128] (Embodiment 3) The embodiment of the present invention also provides a computer storage medium, the computer storage medium can store a program, and when the program is executed by a computer device including a processor, the computer device executes the above-mentioned method embodiment Some or all steps of the risk assessment method described in .

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 relates to a risk evaluation method and system. A valuable weak variable is dug and added into a risk evaluation model, more factors are considered in risk evaluation, the interpretation and stability are higher, the accuracy of risk evaluation can be improved, and the objectivity of risk evaluation is ensured. The method comprises that according to correlation between a data source and a target valuable and / or correlation between the data source and user information, variables are grounded into at least one first type of variable group and at least one second type of variable group; a risk evaluation model is established for the at least one second type of variable group, and a model result of the risk evaluation model of each second type of variable group is obtained; the model result of the risk evaluation model of each second type of variable group serves as a variable and is merged with all quantities in the at least one first type of variable group to form a third type of variable group; and an integrated risk evaluation model is established for the third type of variable group.

Description

technical field [0001] The present invention relates to the technical field of risk assessment based on computer technology, in particular to a risk assessment method and system. Background technique [0002] Risk assessment is an assessment of the possibility of risks brought about by threats, weaknesses, and impacts that information faces. There are two commonly used risk assessment methods: model method and expert method. [0003] The model method refers to the method of constructing a risk assessment model by using machine learning methods such as logistic regression, decision tree, and random forest, and conducting risk assessment based on the model results. Practice has found that some weak variables may be very meaningful in business. However, in the model method, weak variables cannot be selected into the model, resulting in the model method not being able to reflect the role of some variables, and it is difficult to reflect the future trend of business development....

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): G06Q40/02
CPCG06Q40/03G06N20/00G06F17/18G06Q10/0635G16Z99/00
Inventor 刘江
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap