Establishment method of online lending credit risk assessment model based on multi-information source fusion

A risk assessment model and network lending technology, which is applied in the field of establishing a credit risk assessment model for online lending that integrates multiple information sources, and can solve problems such as inability to assess credit risk of online lending, conflicts between information sources and model assessment results, and single information sources. , to achieve the effect of reducing one-sidedness, reducing inconsistency, and high return on investment

Active Publication Date: 2022-03-11
DALIAN UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a method for establishing a network lending credit risk assessment model of multi-information source fusion, which solves the problem that the existing loan credit risk assessment method in the prior art uses a single information source and cannot accurately assess the network lending credit risk. evaluation; and the issue of conflicting evaluation results from different information sources and models

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
  • Establishment method of online lending credit risk assessment model based on multi-information source fusion
  • Establishment method of online lending credit risk assessment model based on multi-information source fusion
  • Establishment method of online lending credit risk assessment model based on multi-information source fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] A method for establishing an online lending credit risk assessment model fused with multiple information sources includes the following steps:

[0070] The first step: measure the loan similarity according to the borrower's information source; starting from the borrower's information source, by extracting the feature vector of the borrower's influence on the credit risk of online lending, and then constructing the loan similarity based on logistic regression and metric learning respectively. sex measurement model;

[0071] The second step: measure the similarity of loans according to the information sources of investors; through the quantification of investor behavior and investment relationship information, the PageRank method and investor composition scores are introduced to evaluate the similarity between loans;

[0072] The third step: the integration of the fused loan similarity information by the minimum reverse order; in the first and second steps, based on diffe...

Embodiment 2

[0076] A method for establishing a credit risk assessment model for online lending based on the fusion of multiple information sources, wherein, the first step is to measure loan similarity according to the borrower's information source, which specifically includes the following steps;

[0077] (1), extract the risk features in the borrower information, and establish the feature vector of the borrower information as X={x 1 , x 2 , x 3 ,...,x 8}, where x 1 , x 2 and x 3 Respectively represent different risk characteristics; the risk characteristics of the borrower information include loan amount, loan interest rate, debt-to-income ratio of the borrower, FICO score of the borrower, current amount owed by the borrower, and default of the borrower in the past seven years Number of times, income of the borrower, number of consultations of the borrower in the last six months;

[0078] (2), according to the logistic regression algorithm to measure the similarity of the borrower...

Embodiment 3

[0092] A method for establishing a credit risk assessment model for online lending based on the fusion of multiple information sources, wherein the second step: measuring the loan similarity according to the investor's information source, specifically includes the following steps:

[0093] (1) Extract the investor's investment behavior and investment relationship information; the information extracted from the investor includes the investment secondary network G, the loan weight matrix Ω, and the investor weight matrix λ, specifically:

[0094] (a), G={U, V, E}, where U and V represent investors and loans respectively, E=(e ij ) m×n are the edges connecting them, each edge e ij The size of the investor u i on loan v j the investment amount;

[0095] (b), Ω=(ω ij ) m×n , where ω ij Indicates that the investor u i on loan v j The investment amount of investor u i The ratio of the total investment amount to n loans is calculated as:

[0096] (c), λ=(λ ij ) m×n , ...

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 for establishing a network lending credit risk assessment model based on the fusion of multiple information sources. Measure the loan similarity; the third step: the integration of the fused loan similarity information by the minimum reverse order. The present invention proves that when the target rate of return continues to increase, the investment portfolio model based on relative entropy constraints always obtains higher investment returns than the classical "mean-variance" portfolio model; in addition, the present invention based on the minimum The loan credit risk assessment model based on the fusion of reverse order pairs can obtain the highest investment return at different target rate of return levels, which further proves the robustness of the online lending credit risk assessment model based on the fusion of multiple information sources, and can help investors obtain more Higher and more stable investment returns.

Description

technical field [0001] The invention relates to a method for establishing a network lending credit risk assessment model fused with multiple information sources. Background technique [0002] With the prosperity of Internet finance, the online lending industry has developed rapidly. As a supplement to traditional lending methods, online lending enables borrowers and lenders to complete loan transactions directly through the online platform, eliminating the need for complex review and transaction procedures in traditional bank lending. By enabling funds to flow directly between borrowers and lenders, borrowers can have lower borrowing rates, while investors can obtain higher investment returns. With the advantages of low threshold and high returns, online lending has attracted the attention of many small and medium-sized enterprises and individual borrowers, which has greatly enhanced the efficiency of capital flow in the market and promoted the development of Internet finan...

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): G06Q40/02
CPCG06Q40/03
Inventor 郭艳红蒋帅陈菲婷
Owner DALIAN UNIV OF TECH
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