Abstract:
This article provides an overview of modern machine learning methods in
the context of their active use in credit scoring, with particular attention to
the following algorithms: light gradient boosting machine (LGBM)
classifier, logistic regression (LR), linear discriminant analysis (LDA),
decision tree (DT) classifier, gradient boosting classifier and extreme
gradient boosting (XGB) classifier. Each of the methods mentioned is
subject to careful analysis to evaluate their applicability and effectiveness in
predicting credit risk. The article examines the advantages and limitations of
each method, identifying their impact on the accuracy and reliability of
borrower creditworthiness assessments. Current trends in machine learning
and credit scoring are also covered, warning of challenges and discussing
prospects. The analysis highlights the significant contributions of methods
such as LGBM classifier, LR, LDA, DT classifier, gradient boosting
classifier and XGB classifier to the development of modern credit scoring
practices, highlighting their potential for improving the accuracy and
reliability of borrower creditworthiness forecasts in the financial services
industry. Additionally, the article discusses the importance of careful
selection of machine learning models and the need to continually update
methodology in light of the rapidly changing nature of the financial market.
