Bank potential credit client mining method based on knowledge graph and machine learning algorithm

A knowledge graph and customer technology, applied in the fields of instruments, computing, marketing, etc., can solve the problems of few applications related to mining potential credit customers and no literature.

Pending Publication Date: 2019-11-15
北京海致星图科技有限公司
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It is understood that although efficient and integrated machine learning algorithms are also widely used in banks, there are relatively few applic

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
  • Bank potential credit client mining method based on knowledge graph and machine learning algorithm
  • Bank potential credit client mining method based on knowledge graph and machine learning algorithm
  • Bank potential credit client mining method based on knowledge graph and machine learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0082] like figure 1 and figure 2 As shown, the method of mining potential credit customers of banks based on knowledge graphs and machine learning algorithms includes the following steps:

[0083] 1. Sample collection stage

[0084] Construct the corporate knowledge graph G(E, V) based on the company's holding relationship, actual controller relationship, concerted action person, close capital relationship, close bill transaction relationship, and close entrusted payment relationship. The attributes of the vertices and various edges are respectively as follows:

[0085] Vertex attributes: name, in-line customer or not;

[0086] Edge attributes of holding relationship: shareholding amount, shareholding ratio, start time, end time;

[0087] The relationship side attributes of the actual controller: start time, end time;

[0088] Attributes of people acting in concert: start time, end time;

[0089] Edge attributes of close capital exchange relationship: transfer amount, ...

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 provides a bank potential credit client mining method based on a knowledge graph and a machine learning algorithm. The method comprises the following steps: 1, a sample collection stage;2, a data preprocessing stage; 3, a model training stage. The method has the advantages that an efficient XGBoost integrated classifier is used for training a potential credit granting customer prediction model, potential credit granting customers with higher marketing success rate are mined, and accurate marketing of the customers is realized; the wide application and popularization of the method provide credit clients with higher marketing values for service personnel, the method improves the work efficiency of front-line service personnel, and has great significance and application valuesfor carrying out credit servicees in banks. A mode of extracting features based on the map is applied to potential credit granting customer mining for the first time, so that the application range ofthe knowledge map is expanded, and the development of the knowledge map is further promoted; and a good effect is achieved for solving the problem of nonuniform sample treatment.

Description

technical field [0001] The invention relates to a method for mining potential credit clients of a bank, in particular, an efficient, accurate, and uniform processing sample method for mining potential credit clients of a bank based on a knowledge map and a machine learning algorithm. Background technique [0002] Credit granting is a prerequisite for enterprises to apply for financing from banks. It is a prerequisite for using bank general loans, trade financing, and supply chain products. High-quality corporate credit granting customers have high stickiness and can bring interest and fee income to banks. . [0003] At present, the main ways for banks to develop credit customers are as follows: first, customers who have credit needs directly go to bank outlets and account managers to consult related services, which are called self-initiated customers; second, bank outlet credit account managers look for credit customers based on interpersonal relationships; There are dedica...

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): G06Q30/02G06Q40/02
CPCG06Q30/0201G06Q40/02
Inventor 周家木
Owner 北京海致星图科技有限公司
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