Kmeans-SMOTE Integration forHandlingImbalance DatainClassifying Financial Distress Companiesusing SVM and Naïve Bayes

Kmeans-SMOTE Integration forHandlingImbalance DatainClassifying Financial Distress Companiesusing SVM and Naïve Bayes

K-means-SMOTE;Data Imbalance;Financial Distress

mbalanced data presents significant challenges in machine learning, leading to biased classification outcomes favouringthe majority class. This issue is especially pronounced in financial distress classification, where data imbalance is common due to the scarcity of such instances in real-world datasets. This study aims to mitigate data imbalance in financial distress companies using the Kmeans-SMOTE method approach by combining K-meansclustering and the Synthetic Minority Oversampling Technique (SMOTE). Various classification approaches, including Naïve Bayes and Support Vector Machine (SVM),are implemented on a financial distress dataset from Kaggle to evaluate the effectiveness of Kmeans-SMOTE. Experimental results show that SVM outperforms Naïve Bayes with impressive accuracy (99.1%), f1-score (99.1%),Area Under Precision-Recall (AUPRC) (99.1%), and Geometric-mean (Gmean) (98.1%). Based on these results, Kmeans-SMOTE canbalance the data effectively, leading to a quite significant improvement in performance

Didit Johar Maulana1, Siti Saadah2, Prasti Eko Yunanto

https://jurnal.iaii.or.id/index.php/RESTI/article/view/5140/892

Departmentof Informatics, Informatics, Telkom University, Bandung, Indonesia

07-02-2024

FAJAR BAGUS W

PDF

ENGLISH

TEXT