IMPLEMENTASI METODE BALANCING DATA DENGAN TEKNIK SMOTETOMEK DALAM KLASIFIKASI PENYAKIT DIABETES MENGGUNAKAN ALGORITMA XGBOOST

Kusumajati, Fatwa Ratantja (2025) IMPLEMENTASI METODE BALANCING DATA DENGAN TEKNIK SMOTETOMEK DALAM KLASIFIKASI PENYAKIT DIABETES MENGGUNAKAN ALGORITMA XGBOOST. Undergraduate thesis, UPN "Veteran" Jawa Timur.

[img] Text (Cover)
cover.pdf

Download (1MB)
[img] Text (BAB 1)
bab 1.pdf

Download (271kB)
[img] Text (BAB 2)
bab 2.pdf
Restricted to Registered users only until 5 June 2028.

Download (742kB)
[img] Text (BAB 3)
bab 3.pdf
Restricted to Registered users only until 5 June 2028.

Download (570kB)
[img] Text (BAB 4)
bab 4.pdf
Restricted to Registered users only until 5 June 2028.

Download (1MB)
[img] Text (BAB 5)
bab 5.pdf

Download (254kB)
[img] Text (Daftar Pustaka)
daftar pustaka.pdf

Download (258kB)
[img] Text (Lampiran)
lampiran.pdf
Restricted to Registered users only until 5 June 2028.

Download (309kB)

Abstract

This work uses 2,000 patient data points from Kaggle, including demographic and medical information, to improve the accuracy of diabetes categorization using the XGBoost algorithm and the SMOTETomek method. In Indonesia, diabetes is a serious public health issue. One of the main problems with this study is the unbalanced dataset, which has more non-diabetic samples than diabetic ones. In order to balance class distributions, the SMOTETomek approach is used, which combines Tomek Links with SMOTE (Synthetic Minority Over- sampling Technique) to oversample the minority class and eliminate borderline data. While minority class accuracy is marginally decreased (0.97 vs. 0.99 for SMOTE and original data), the results show that SMOTETomek increases XGBoost accuracy to 95.01%, surpassing both SMOTE and the original data (92.13%). Nonetheless, it continues to retain a high F1-score and accuracy, demonstrating its ability to manage data imbalance with few compromises.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorRahmat, BasukiNIDN5972549basukirahmat.if@upnjatim.ac.id
Thesis advisorJunaidi, AchmadNIDN0710117803achmadjunaidi.if@upnjatim.ac.id
Subjects: Q Science > QA Mathematics > QA76.6 Computer Programming
Divisions: Faculty of Computer Science > Departemen of Informatics
Depositing User: Fatwa Ratantja Kusumajati
Date Deposited: 05 Jun 2025 03:36
Last Modified: 05 Jun 2025 03:36
URI: https://repository.upnjatim.ac.id/id/eprint/37123

Actions (login required)

View Item View Item