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

Method and device for determining eigenvalues ​​of a fraudulent transaction model

A technology of eigenvalues ​​and transactions, applied in the field of data processing, can solve problems such as low accuracy, achieve the effects of improving accuracy, avoiding insufficient model learning, and improving reliability

Active Publication Date: 2021-08-27
CHINA UNIONPAY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a method and device for determining a characteristic value of a fraudulent transaction model, so as to solve the technical problem in the prior art that the characteristic calculation only considers a single transaction element, resulting in low accuracy

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
  • Method and device for determining eigenvalues ​​of a fraudulent transaction model
  • Method and device for determining eigenvalues ​​of a fraudulent transaction model
  • Method and device for determining eigenvalues ​​of a fraudulent transaction model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments . Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0072] figure 1 It exemplarily shows a schematic flowchart corresponding to a method for determining a characteristic value of a fraudulent transaction model provided by an embodiment of the present invention, including the following steps:

[0073] Step 101, acquire a sample set of transaction data according to set rules, and the sample set includes normal transaction data and fraudulent transaction data.

[0074] Step 102, for each tran...

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 method and device for determining the characteristic value of a fraudulent transaction model. The method includes: for each transaction element for which transaction data is obtained according to set rules, determining the first occupancy rate of each attribute value of the transaction element in the sample set, and then determining the attribute according to the first occupancy rate of the attribute value value as the benchmark attribute value, and combine the benchmark attribute values ​​to obtain the transaction behavior rules; then determine the benchmark transaction behavior rules according to the second occupancy rate, and determine the fraud identification degree of each benchmark behavior rule in the sample set to determine each transaction The eigenvalues ​​corresponding to the behavior rules. In the present application, various transaction elements are comprehensively considered to expand the information volume of feature technology, improve the reliability of the source of feature values ​​corresponding to transaction data, and thereby improve the accuracy of model detection.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method and device for determining a characteristic value of a fraudulent transaction model. Background technique [0002] With the development of Internet finance, mobile payment and online transactions are gradually popularized, followed by more and more fraudulent transactions. Many unscrupulous people complete fraud by forging transaction vouchers and stealing transaction passwords through Internet transaction channels. trade. The prevalence of fraudulent transactions will increase financial risks, be detrimental to the stability of the financial order, and cause serious losses to cardholders and financial institutions. In order to avoid this problem, it is necessary to accurately identify fraudulent transactions. [0003] At present, samples are obtained from transaction data, a fraudulent transaction model is trained through the samples, and fraudulent transaction...

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): G06Q20/40G06Q40/04G06K9/62
CPCG06Q20/4016G06Q40/04G06F18/22
Inventor 杜金泉周继恩陆堃彪
Owner CHINA UNIONPAY
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