A method of establishing enterprise default risk model based on xgboost

A technology of risk model and establishment method, applied in the establishment of enterprise default risk model, can solve problems such as unavoidable errors, limitations of business application, poor model portability, etc., and achieve good results

Active Publication Date: 2022-08-05
NANJING UNIV OF SCI & TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In summary, most of the existing credit risk assessment models are still based on manual scorecards, and staff build models based on experience. Such models have poor portability and limited business application
There are no mature data mining models reported yet, so it is impossible to solve complex business process-oriented problems, and it is difficult to avoid errors caused by human experience

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
  • A method of establishing enterprise default risk model based on xgboost
  • A method of establishing enterprise default risk model based on xgboost
  • A method of establishing enterprise default risk model based on xgboost

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0085] combine figure 1 , the present invention is based on the establishment method of the enterprise default risk model of xgboost, comprising the following steps:

[0086] Step 1: Arrange the source data and splicing them according to the month to form the wide table L1 of the enterprise, as follows:

[0087] The organization of the wide table is as follows figure 2 . Sort out the source data, splicing it according to the month, read the data of the enterprise in turn, and obtain the horizontal wide table data L1 of the enterprise according to the month. The data contains the same features, that is, each piece of data σ={t 1 ,t 2 ,t 3 ,…,t r }, t 1 ...t r For data of different months, the number of features and feature fields in t are the same.

[0088] Step 2, combine image 3 , use the custom sliding window function to cut the wide table L1 to form the enterprise sliding window data L2, as follows:

[0089] Step 2-1, analyze the table L1, and define a sliding ...

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 an enterprise default risk model based on xgboost. The method is as follows: firstly, the source data are sorted and spliced ​​according to the month to form the wide table L1 of the enterprise. Any piece of data is the collection of the enterprise in the order of increasing natural months, and the data of each month contains the same characteristics; then Use the custom sliding window function to cut the wide table L1 to form the enterprise sliding window data L2; finally, use the xgboost algorithm to use the sliding window data L2 to model and optimize the model. The method of the invention can improve the prediction accuracy of the enterprise default risk model, and establish a risk control model with good effect.

Description

technical field [0001] The invention relates to the technical field of enterprise risk control, in particular to a method for establishing an enterprise default risk model based on xgboost. Background technique [0002] With the wide application of machine learning, data mining technology is changing the prediction mode of default risk. Different from the "hard information" involving statistical characteristics and financial indicators used by traditional methods, the risk model based on data mining technology can be calculated by the computer itself. Identify important features and add various soft information to the model to help computers better predict corporate default risk. The application of data mining technology is bound to have a huge impact on the traditional risk credit assessment system. [0003] Compared with the traditional credit risk assessment model, the data mining model has three main advantages. First, most of the traditional credit risk assessment mod...

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): G06Q10/06G06Q40/02G06Q10/04
CPCG06Q10/04G06Q10/0635G06Q40/03
Inventor 李千目董潇刘奕婧
Owner NANJING UNIV OF SCI & 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