Open AccessCredit Risk Management Using Automatic Machine Learning
Author(s) -
Bartłomiej Gaweł,
Andrzej Paliński
Publication year - 2020
Publication title -
decision making in manufacturing and services
Language(s) - English
Resource type - Journals
eISSN - 2300-7087
pISSN - 1896-8325
DOI - 10.7494/dmms.2020.14.2.4379
Subject(s) - credit card , computer science , credit risk , logit , automation , logistic regression , process (computing) , data mining , software , risk management , quality (philosophy) , machine learning , model risk , artificial intelligence , finance , engineering , business , world wide web , mechanical engineering , philosophy , epistemology , payment , programming language , operating system
The article presents the basic techniques of data mining implemented in typical commercial software. They were used to assess the risk of credit card debt repayment. The article assesses the quality of classification models derived from data mining techniques and compares their results with the traditional approach using a logit model to assess credit risk. It turns out that data mining models provide similar accuracy of classification compared to the logit model, but they require much less work and facilitate the automation of the process of building scoring models.