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

A customer risk feature screening method based on svm-rfe and its application

A feature screening and customer technology, applied in the field of level, can solve the problem of redundant information without reference to the training feedback results of the learner

Active Publication Date: 2022-08-02
SHANGHAI UNIV OF ENG SCI +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the defect that the existing technology does not consider redundant information between features and does not refer to the training feedback results of the learner, and provides a method that can use machine learning to complete automatic screening and quantitative identification of customer risk features

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
  • A customer risk feature screening method based on svm-rfe and its application
  • A customer risk feature screening method based on svm-rfe and its application
  • A customer risk feature screening method based on svm-rfe and its application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] A customer risk feature screening method based on SVM-RFE, the steps are as follows figure 1 shown, specifically:

[0096] (1) Obtain customer risk characteristic data including multiple customer characteristics;

[0097] Customer risk characteristic data can be obtained through the following channels: financial institutions' own data platforms, third-party data platforms, and collection of customer risk characteristic data using web crawlers and text data analysis;

[0098] Collecting customer risk profile data using web crawler and text data analysis includes the following steps:

[0099] Collect customer risk cases → analyze customer risk cases → excavate customer risk characteristics;

[0100] Specifically, the collection of customer risk cases may be to use web crawler technology to crawl customer risk cases on mainstream websites, or to collect customer risk cases manually through channels such as public publications;

[0101] Analysis of customer risk cases ca...

Embodiment 2

[0160] an electronic device such as figure 2 shown, including one or more processors, one or more memories, one or more programs, data collection means, and a display device connected to the processors;

[0161] The data collection device is used to obtain customer risk characteristic data including a plurality of customer characteristics, the display device is used to display the finally obtained set of customer risk characteristics, one or more programs are stored in the memory, and when the one or more programs are processed by the processor During execution, the electronic device is made to execute the customer risk feature screening method based on SVM-RFE as described in Embodiment 1.

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 customer risk feature screening method based on SVM-RFE and its application. The method includes: acquiring customer risk feature data including multiple customer features; j , calculate the customer risk feature X based on the Gini coefficient, information gain, information gain ratio, mutual information and the feature weight of the optimal classification result of the SVM classifier j After calculating the importance comprehensive metric index of all customer risk features in turn, sort them in descending order according to the above indexes, and select the first k features to form the customer risk feature set. The method of the invention not only considers the correlation between the selected feature subset and the target variable and the redundancy of the feature subset itself, and overcomes the drawback of using a single index to screen customer risk characteristics, but also introduces the SVM classifier in the feature screening process. The training results of the selected customer risk characteristics are more suitable for the characteristics of the SVM classifier, and the application prospect is good.

Description

technical field [0001] The invention belongs to the technical field of customer risk level (CRR), and relates to a customer risk feature screening method based on SVM (Support vector machine, support vector machine)-RFE (Recursive feature elimination, recursive feature elimination) and its application. Background technique [0002] With the continuous development of Internet technology, more and more financial institutions, enterprises, merchants and ordinary users are more and more accustomed to using Internet finance to realize various financial transactions, such as inter-bank transfer, online payment, online investment and wealth management, digital Currency, online shopping, and more. [0003] But on the other hand, there are also many problems in Internet finance. First of all, Internet finance has not yet been connected to the People's Bank of China's credit information system, nor does it have a credit information sharing mechanism, nor does it have a risk control, ...

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 Patents(China)
IPC IPC(8): G06F16/951G06F16/2458G06K9/62G06Q40/04
CPCG06F16/951G06F16/2465G06Q40/04G06F18/2411
Inventor 王国强罗康洋张怡谢晓金施兴森李金姚兵李梦颖
Owner SHANGHAI UNIV OF ENG SCI
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