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

Personal credit risk measurement model based on GA-BP

A GA-BP, measurement model technology, applied in the field of personal credit risk measurement model, can solve problems such as low prediction accuracy, achieve the effects of improving accuracy and reliability, preventing market risks, and good application value

Pending Publication Date: 2022-03-01
东北大学秦皇岛分校
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies of the prior art, the present invention provides a personal credit risk measurement model based on GA-BP, which solves the problem of low prediction 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
  • Personal credit risk measurement model based on GA-BP
  • Personal credit risk measurement model based on GA-BP
  • Personal credit risk measurement model based on GA-BP

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] Such as Figure 1-2 As shown, the embodiment of the present invention provides a GA-BP-based personal credit risk measurement model, including the GA-BP model, the GA-BP model based on the new model of the BP neural network principle and genetic algorithm, the genetic algorithm is different from the local search of neural network. The algorithm, the genetic algorithm uses an efficient parallel global search algorithm, which can automatically obtain and accumulate knowledge about search space during searching, so that it can avoid local minimal values, which can be processed. Any form of target functions and constraints can operate any structural objects within the global scope, so there is a faster comparative speed. Genetics requires optimized solutions to form a group, and performs selection, crossings and variation operations of these coding groups, resulting in a more optimal solution, so that the algorithm is described until the algorithm is terminated. .

[0038] The B...

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 personal credit risk measurement model based on GA-BP, and relates to the technical field of finance. The personal credit risk measurement model based on GA-BP comprises a GA-BP model, the GA-BP model is a novel model based on a BP neural network principle and a genetic algorithm, the genetic algorithm is different from a local search algorithm of a neural network, and an efficient parallel global search algorithm is adopted in the genetic algorithm. Knowledge related to a search space can be automatically obtained and accumulated in the search process, and the global optimization ability is good, so that falling into a local minimum value can be avoided, target functions and constraints in any form can be processed, any structural object can be operated in a global range, and the operation speed is high. The genetic algorithm encodes the solution, needing to be optimized, of the target function to form a group. Effective early warning signals can be provided for commercial banks, market risks can be prevented, and the method has good application value.

Description

Technical field [0001] The present invention relates to the field of financial technologies, specifically a personal credit risk measurement model based on GA-BP. Background technique [0002] Credit risk is one of the most important risks facing financial institutions. After the traditional proportion analysis, after subjective analysis, the statistical method is widely used, such as the discrimination analysis, Logit regression analysis. Since the end of the 1980s, artificial intelligence technology has been applied to credit risk measurements. Currently, the most widely used in this field is the BP neural network, nonlinear mapping capabilities make it unique. However, the parameter setting of the BP neural network is based on the local information of the parameter space, which is easily trapped into the local extract, which will reduce the convergence speed and prediction accuracy. Inventive content [0003] (1) Solving technical issues [0004] In response to the shortcomin...

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): G06Q40/02G06N3/08G06N3/04
CPCG06N3/084G06N3/086G06N3/048G06Q40/03
Inventor 吴琼玉李事成孙福权
Owner 东北大学秦皇岛分校
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