Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Car loan risk control model generation method and device and score card generation method

A model generation and scorecard technology, applied in the field of credit risk control, which can solve problems such as no big data risk control solution yet

Pending Publication Date: 2021-10-26
浙江惠瀜网络科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current vigorous development of Internet finance has spawned a large number of data risk control methods. However, the risk control technology on the market mainly serves the personal credit business. For specific financial scenarios, especially the vehicle installment scenario of banks, there is no effective solution. Big Data Risk Control Solution

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
  • Car loan risk control model generation method and device and score card generation method
  • Car loan risk control model generation method and device and score card generation method
  • Car loan risk control model generation method and device and score card generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] The present invention proposes a method for generating a car loan risk control model. The method includes: obtaining the basic data of the original car loan user; performing feature engineering processing on the basic data; The regression model is trained until the KS value of the logistic regression model reaches the first preset threshold, and the AUC value reaches the second preset threshold, so as to obtain the LR scorecard model, and use the LR scorecard model as a car loan risk control Model.

[0063] According to the current existing problems, this embodiment formulates a method for generating a car loan risk control model. The logistic regression algorithm can predict the default risk of the car loan scene and provide an effective measurement method for the access of the car loan business. .

[0064] In a specific embodiment, such as figure 2 As shown, the method includes:

[0065] S10. Obtain the basic data of the original car loan user, wherein the basic d...

Embodiment 2

[0119] refer to Figure 7 , as an implementation of the method for generating the above-mentioned car loan risk control model, this application provides an embodiment of a device for generating a car loan risk control model. figure 2 The method embodiments shown correspond.

[0120] Such as Figure 7 As shown, the car loan risk control model generation device of this embodiment includes:

[0121] The obtaining module is used to obtain the basic data of the original car loan user;

[0122] A feature engineering processing module, configured to perform feature engineering processing on the basic data;

[0123] A model generation module, configured to train using a logistic regression model based on the feature engineering processed data until the KS value of the logistic regression model reaches a first preset threshold, and the AUC value reaches a second preset threshold , get the LR scorecard model, and use the LR scorecard model as the car loan risk control model.

[01...

Embodiment 3

[0127] The LR scorecard model is a linear classification model based on logistic regression. It adopts binning and discretization methods and WOE value interval coding. Under the premise of processing and intervention by modelers and business experts, it can have High predictive performance is a classic algorithm model widely used in the field of credit risk control, such as scoring the credit level of customers.

[0128] Such as Figure 8 As shown, the application provides a method for generating a scorecard, the method comprising:

[0129] S130. For each characteristic variable of the car loan risk control model described in Embodiment 1 and Embodiment 2, compare the regression coefficient of the car loan risk control model with the WOE value corresponding to each binning interval of the characteristic variable Multiply to get the score of the binning interval

[0130] S132. Perform standard normalization on the scores to obtain a standard score card.

[0131] In a specif...

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 embodiment of the invention discloses a car loan risk control model generation method and device and a score card generation method. The method comprises the following steps: S10, acquiring basic data of an original car loan user; s20, performing feature engineering processing on the basic data; and S30, training by adopting a logistic regression model based on the data after the feature engineering processing until the KS value of the logistic regression model reaches a first preset threshold value and the AUC value reaches a second preset threshold value, obtaining an LR score card model, and taking the LR score card model as a car loan risk control model. The car loan risk control model generation method is formulated for the existing problems at present, the default risk of a car loan scene is predicted by adopting a logistic regression algorithm, and an effective measurement means is provided for admission of car loan business.

Description

technical field [0001] The invention relates to the field of credit risk control. More specifically, it relates to a method and device for generating a car loan risk control model, a method for generating a scorecard, computer equipment, and a storage medium. Background technique [0002] The car loan business is that the borrower pays a certain percentage of the down payment when purchasing a consumer car for self-use. The shortfall is the RMB loan business issued by the bank and paid directly to the car dealers. This type of loan generally has a short repayment cycle, high requirements for customer qualifications, and a large amount of lending funds, which requires a high level of risk control capabilities. With the continuous growth of the automobile market, the bank's car loan business is growing rapidly. With limited personnel and equipment and growing business needs, more intelligent methods are needed to control business risks without affecting business growth. The...

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
IPC IPC(8): G06Q40/02G06Q10/06
CPCG06Q10/0635G06Q40/03
Inventor 周波徐栋郭能蔡浴泓余勇辉
Owner 浙江惠瀜网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com