Investigating the Effect of Class Balancing Methods on the Performance of Machine Learning Techniques: Credit Risk Application
İzmir Yönetim Dergisi · 2024
DOI: 10.56203/iyd.1436742 ↗Kurz gefasst
Fachartikel in der Zeitschrift İzmir Yönetim Dergisi, 2024. Verfasst von Migraç Enes Furkan Milli und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben.
Abstract (Originalsprache)
Credit risk arises as a result of the failure of the loans given by banks to the customers to fulfill their obligations at the end of the specified term. Technological advances allow the use of machine learning methods in various sectors. These methods aim to facilitate the identification of customers at risk with the system adapted to the creditworthiness processes of banks. For this purpose, in order to make the most appropriate evaluation in the lending process of banks, re-sampling techniques to eliminate the problem of class imbalance encountered in unbalanced data sets were made balanced and their effects on machine learning were investigated. During the implementation phase, German, Australian and HMEQ credit data sets were used. Different machine learning classification methods such as Logistic Regression (LR), K-Narest Neighbor (KNN), Naive Bayes (NB), Support Vector Machines (SVM), Multilayer Perceptron (MLP), Decision Trees (DT), Random Forests (RF), Gradient Boosting Decision Trees (GBDT), Extremely Randomized Trees, Hard and Soft Voting were used to detect risky customers. The problem of class imbalance was balanced with resampling and hybrid techniques such as Random Oversampling (ROS), Random Undersampling (RUS), Balanced Bagging Classifier (BBC), SMOTE-Tomek Links and SMOTE-ENN. In this context, the performances of three different data sets were examined in four different scenarios. As a result of the study, the hybrid method, in which oversampling and undersampling methods are used together for the class balancing problem, showed the best classification performance among machine learning techniques.
Zitieren
APA
Milli, M. E. F., Aras, S., & Kocakoç, İ. D. (2024). Investigating the Effect of Class Balancing Methods on the Performance of Machine Learning Techniques: Credit Risk Application. İzmir Yönetim Dergisi. https://doi.org/10.56203/iyd.1436742
Vancouver
Milli MEF, Aras S, Kocakoç İD. Investigating the Effect of Class Balancing Methods on the Performance of Machine Learning Techniques: Credit Risk Application. İzmir Yönetim Dergisi. 2024. doi:10.56203/iyd.1436742
BibTeX
@article{Milli2024,
author = {Milli, Migraç Enes Furkan and Aras, Serkan and Kocakoç, İpek Deveci},
title = {Investigating the Effect of Class Balancing Methods on the Performance of Machine Learning Techniques: Credit Risk Application},
journal = {İzmir Yönetim Dergisi},
year = {2024},
doi = {10.56203/iyd.1436742}
}
EUVIMED