Scoring for legal entities

Assessment of the probability of default of a legal entity, depending on whether the borrower was previously issued court decisions and what their content was, both as a plaintiff and as a defendant.

This decision is particularly useful for assessing the risk of issuing a credit to borrowers whose credit history is either uninformative or absent.

Contents
Identification
Borrower’s current ID data and the history of changes made to it.
Scoring
A value from 0 to 1 that determines the probability of late payments of over 100 UAH that are at least 90 days past due within a 12-month period on a loan being considered.
Model
Target function
Late payment of over 100 UAH at least 90 days past due within.
Predictors
Data from public sources, credit history
Method
Intellectual analysis of the text and tonality analysis, gradient boost
0.84
ROC-AUC “plaintiff”
0.795
ROC-AUC “defendant”
Default probability based on scoring
The plaintiff model
The defendant model
Working with the scoring

To build a scoring, the following is required:

Sample for model training. The required number of records is 10,000 or more;

Sample markup into “good” and “bad”;

Description of the business process for scoring application;

Description of data for model training.

Details and terms of development are negotiated individually.

XML
XML format is used to work with scoring.
 
General structure of interaction:
 
Http Method
 
POST
 
Request URL
 
 
Test URL
 
 
Request   
 
 
Response
 

 

Would you like to know everything about your counterparties and protect yourself from fraud?
Become our partner!
Application sent. Please expect during the day you will be contacted.