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

Financial fraud gang identification method based on hypergraph segmentation

A recognition method and graph segmentation technology, applied in the fields of financial anti-fraud and machine learning, to achieve the effect of improving iteration efficiency

Pending Publication Date: 2021-04-16
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a method for identifying financial fraud gangs based on hypergraph segmentation to solve the limitations of traditional methods that only consider local feasibility due to the use of ordinary graphs and how to efficiently calculate for high-order information networks. question

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
  • Financial fraud gang identification method based on hypergraph segmentation
  • Financial fraud gang identification method based on hypergraph segmentation
  • Financial fraud gang identification method based on hypergraph segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0030] The technical solution adopted by the present invention is a method for identifying financial fraud gangs based on hypergraph segmentation. Step S1, feature extraction: from the original data of call records, factors such as contact ID, call duration, and number of calls are extracted to form a JSON string form;

[0031] Step S2, data standardization processing: the first rule is that when the calling ID is the same as the called party, the record does not meet the specification and the record is deleted; the second rule is that the end time - start time ≠ call duration or the end time is earlier than the start time time, delete records;

[0032] Step S3, data cleaning: delete call records such as harassment, express delivery, meal delivery, sales promotion, invalid numbers, service numbers, etc.;

[0033] Step S4, data storage: store the cle...

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 financial fraud gang identification method based on hypergraph segmentation. According to the method, a hypergraph segmentation process is decomposed into six sub-processes: feature extraction, data normalization processing, data cleaning, data storage, index selection and call network construction, adjacent matrix construction, non-negative matrix decomposition and result acquisition. The method is implemented on the basis of the concept of a multi-node hypergraph on one side, the property of the hypergraph enables the model to obtain an approximate value of a globally optimal solution, and most of current gang fraud recognition schemes are algorithms based on traditional graphs and can only consider the locally optimal solution. And the gang detection field is more dependent on a globally optimal solution. For a high-latitude calculation scheme, a hypergraph regular term is added into a loss function of non-negative matrix factorization, high-dimensional information can be coded, and the iteration efficiency is improved.

Description

technical field [0001] The invention belongs to the related fields of financial anti-fraud and machine learning, and is an effective method for identifying financial fraud gangs. Background technique [0002] In the field of Internet finance, fraud is the most important factor causing losses to lending institutions. Studies have found that credit fraud is often committed by gangs, and these gangs are directly and inextricably linked. [0003] It is more feasible and effective to use operator data to analyze customer social behaviors and find traces of fraudulent gangs. However, operator communication data is often huge, and general statistical methods cannot be used for effective analysis. Machine learning technology is needed to conduct Divide the customer base and look for fraudulent gangs. The hypergraph breaks the ordinary graph describing the binary relationship. A hyperedge can contain multiple vertices, which is more suitable for describing the multivariate relations...

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): G06F16/901G06F16/215G06F16/9035G06F16/907
Inventor 张涛张宗旺
Owner BEIJING UNIV OF TECH