Deep-learning-oriented network personal credit fraud behavior detection method

A deep learning and detection method technology, applied in the field of computer science, can solve the problems of poor noise resistance and robustness, achieve strong noise resistance and robustness, and improve the effect of fraud detection

Active Publication Date: 2019-09-24
WUHAN UNIV
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application solves the problem of poor noise resistance and robustness of the network loan fraud detection algorithm in the prior art by providing a deep learning-oriented network personal credit fraud detection method

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
  • Deep-learning-oriented network personal credit fraud behavior detection method
  • Deep-learning-oriented network personal credit fraud behavior detection method
  • Deep-learning-oriented network personal credit fraud behavior detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to better understand the above-mentioned technical solution, the above-mentioned technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0055] please see figure 1 A kind of deep learning-oriented network personal credit fraud detection method provided by the invention comprises the following steps:

[0056] Step 1. Obtain historical online personal credit information;

[0057] Step 2, select the first sub-parameter of the denoising gradient boosting tree;

[0058] Step 3, train the denoising gradient boosting tree, use the historical network personal credit information for unsupervised learning, and obtain the first data feature;

[0059] Step 4, use the first data feature to carry out supervised learning, and complete the training of the denoising gradient boosting tree model;

[0060] Step 5, storing the denoising gradient boosting tree model;

[0061] Step 6. Input new net...

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 belongs to the technical field of computer science, and discloses a deep-learning-oriented network personal credit fraud behavior detection method, which comprises the following steps: obtaining historical network personal credit information; selecting a first sub-parameter of the noise reduction gradient lifting tree; training the noise reduction gradient lifting tree, and carrying out unsupervised learning by using historical network personal credit information to obtain a first data feature; performing supervised learning by using the first data feature to complete noise reduction gradient lifting tree model training; storing the noise reduction gradient lifting tree model; and inputting new network personal credit information, and detecting the fraud behavior through the noise reduction gradient lifting tree model. The deep-learning-oriented network personal credit fraud behavior detection method has higher noise resistance and robustness, and can improve the fraud detection effect of network personal credit.

Description

technical field [0001] The invention relates to the field of computer science and technology, in particular to a deep learning-oriented network personal credit fraud detection method. Background technique [0002] In the field of fraud risk assessment, empirical discriminant analysis was first adopted in foreign countries, mainly relying on the experience and ability of professional assessors. Since the entire assessment process has not been quantitatively analyzed and there is strong subjectivity, the prediction results are often not accurate. ideal. With the improvement of computer computing speed, disciplines such as computer science, economics, and statistics have also become more and more integrated, and a large number of statistical modeling methods and data analysis techniques have been completed on computers. In the study of fraud risk assessment models, Pallavi Kulkarni and Roshani Ade established a classification model based on Logistic regression. Logistic regres...

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): G06Q40/02G06N3/08
CPCG06N3/08G06Q40/03
Inventor 胡文斌唐传慧过冰峰
Owner WUHAN UNIV
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