Optimasi Extreme Gradient Boosting Menggunakan SMOTE-ENN dan Hyperparameter Tuning Optuna untuk Prediksi Penyakit Jantung

Maulinda, Mutya Anissa (2026) Optimasi Extreme Gradient Boosting Menggunakan SMOTE-ENN dan Hyperparameter Tuning Optuna untuk Prediksi Penyakit Jantung. Undergraduate thesis, UPN Veteran Jawa Timur.

[img] Text (Cover)
21081010154.-cover.pdf

Download (1MB)
[img] Text (Bab 1)
21081010154.-bab1.pdf

Download (244kB)
[img] Text (Bab 2)
21081010154.-bab2.pdf
Restricted to Repository staff only until 13 November 2028.

Download (699kB) | Request a copy
[img] Text (Bab 3)
21081010154.-bab3.pdf
Restricted to Repository staff only until 13 November 2028.

Download (780kB) | Request a copy
[img] Text (Bab 4)
21081010154.-bab4.pdf
Restricted to Repository staff only until 13 November 2028.

Download (1MB) | Request a copy
[img] Text (Bab 5)
21081010154.-bab5.pdf

Download (216kB)
[img] Text (Daftar Pustaka)
21081010154.-daftarpustaka.pdf

Download (247kB)
[img] Text (Lampiran)
21081010154.-lampiran.pdf
Restricted to Repository staff only

Download (138kB) | Request a copy

Abstract

Heart disease is one of the leading causes of death worldwide, making the development of accurate predictive models important in the field of machine learning. Model performance can be affected by differences in class distribution and suboptimal hyperparameter selection. This study aims to improve the performance of XGBoost for heart disease prediction through the application of Synthetic Minority Oversampling Technique-Edited Nearest Neighbors (SMOTE-ENN) and hyperparameter optimization using Optuna based on the Tree structured Parzen Estimator (TPE). The dataset used in this study was obtained from the UCI Machine Learning Repository. Model evaluation was performed using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC) across several data-splitting ratios and k-fold cross-validation settings. The results showed that the combination of SMOTE-ENN and Optuna achieved the best performance, with average accuracy 97,65%, precision 97,52%, recall 97,34%, F1-score 97,43%, dan AUC 99,77%. These results indicate that the application of SMOTE-ENN combined with Optuna hyperparameter optimization can improve the performance of XGBoost for heart disease prediction.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorNugroho, BudiNIDN0707098003budinugroho.if@upnjatim.ac.id
Thesis advisorJunaidi, AchmadNIDN0710117803achmadjunaidi.if@upnjatim.ac.id
Subjects: T Technology > T Technology (General)
Divisions: Faculty of Computer Science > Departemen of Informatics
Depositing User: Mutya Anissa Maulinda
Date Deposited: 13 Nov 2026 07:10
Last Modified: 13 Nov 2026 07:10
URI: https://repository.upnjatim.ac.id/id/eprint/61350

Actions (login required)

View Item View Item