eprintid: 96574
rev_number: 18
eprint_status: archive
userid: 599
dir: disk1/00/09/65/74
datestamp: 2025-08-05 06:50:46
lastmod: 2025-08-05 06:50:46
status_changed: 2025-08-05 06:50:46
type: thesis
metadata_visibility: show
creators_name: RAHMAN, RAVI ADITYA
creators_nimnip: 41521010052
creators_id: raviadityarahman13@gmail.com
contributors_type: http://www.loc.gov/loc.terms/relators/THS
contributors_name: Hakim, Lukman
contributors_nidn: 0327107701
contributors_id: lib.mercubuana.ac.id
title: IMPLEMENTASI METODE STACKING MENGGUNAKAN RANDOM FOREST DAN XGBOOST UNTUK MENGKLASIFIKASI RISIKO SERANGAN JANTUNG
ispublished: pub
subjects: S006.31
subjects: S025.46
subjects: S518.1
subjects: S616.1
divisions: 415
full_text_status: restricted
keywords: Serangan Jantung, Klasifikasi, Stacking, Random Forest, XGBoost.
abstract: Heart attack disease is one of the leading causes of death in the world and is a
significant burden on the health system in Indonesia. Accurate early detection is
essential in preventing and managing the risk of heart attack. This study aims to
develop a heart attack risk classification model by applying the ensemble learning
method using the stacking approach, which combines two machine learning
algorithms, namely the Random Forest and XGBoost algorithms. The dataset used
is secondary data entitled "Heart Attack Prediction in Indonesia" downloaded from
Kaggle, with a total of 158,355 individual data. The research process includes data
preprocessing stages, such as categorical variable numbering, normalization using
MinMaxScaler, and class balancing. The Random Forest and XGBoost models
were each evaluated individually before being combined using the stacking
technique with XGBoost as a meta-learner. Performance evaluation was carried
out using cross validation and metrics of accuracy, precision, recall, and F1-score.
The results showed that the stacking model produced the highest accuracy of 85%,
better than the Random Forest (76%) and XGBoost (74%) models. Feature
importance analysis shows that features such as history of heart disease,
hypertension, and cholesterol levels have significant contributions in the
classification process. The results of this study prove that the application of the
stacking method can improve the performance of machine learning algorithm
models in the classification of heart attack disease.
Keywords: Heart Attack, Classification, Stacking, Random Forest, XGBoost.

Penyakit serangan jantung merupakan salah satu penyebab kematian utama di dunia
dan menjadi beban signifikan bagi sistem kesehatan di Indonesia. Deteksi dini yang
akurat sangat penting dalam upaya pencegahan dan pengelolaan risiko serangan
jantung. Penelitian ini bertujuan untuk mengembangkan model klasifikasi risiko
serangan jantung dengan menerapkan metode ensemble learning menggunakan
pendekatan stacking, yang menggabungkan dua algoritma machine learning yaitu
algoritma Random Forest dan XGBoost. Dataset yang digunakan adalah data
sekunder berjudul “Heart Attack Prediction in Indonesia” yang diunduh dari
Kaggle, dengan total 158.355 data individu. Proses penelitian mencakup tahapan
data preprocessing, seperti penomoran variabel kategorikal, normalisasi
menggunakan MinMaxScaler, dan penyeimbangan kelas. Model Random Forest
dan XGBoost masing-masing dievaluasi secara individual sebelum digabungkan
menggunakan teknik stacking dengan XGBoost sebagai meta-learner. Evaluasi
kinerja dilakukan menggunakan cross validation dan metrik akurasi, presisi, recall,
serta F1-score. Hasil menunjukkan bahwa model stacking menghasilkan akurasi
tertinggi sebesar 85%, lebih baik dibandingkan model Random Forest (76%) dan
XGBoost (74%). Analisis feature importance menunjukkan bahwa fitur-fitur
seperti riwayat penyakit jantung, hipertensi, dan kadar kolesterol memiliki
kontribusi signifikan dalam proses klasifikasi. Hasil penelitian ini membuktikan
bahwa penerapan metode stacking dapat memberikan peningkatan kinerja model
algoritma machine learning dalam klasifikasi penyakit serangan jantung.
Kata kunci: Serangan Jantung, Klasifikasi, Stacking, Random Forest, XGBoost.
date: 2025-07-19
date_type: published
pages: 49
institution: Universitas Mercu Buana Jakarta
department: Biro Perpustakaan
thesis_type: s1
thesis_name: tugas_akhir
kampus: meruya
call_number_cd: FIK/INFO. 25 116
kota: Jakarta
kolasi: xii, 49 hlm
citation:   RAHMAN, RAVI ADITYA  (2025) IMPLEMENTASI METODE STACKING MENGGUNAKAN RANDOM FOREST DAN XGBOOST UNTUK MENGKLASIFIKASI RISIKO SERANGAN JANTUNG.  S1 thesis, Universitas Mercu Buana Jakarta.   
document_url: http://repository.mercubuana.ac.id/96574/1/01%20COVER.pdf
document_url: http://repository.mercubuana.ac.id/96574/2/02%20BAB%201.pdf
document_url: http://repository.mercubuana.ac.id/96574/3/03%20BAB%202.pdf
document_url: http://repository.mercubuana.ac.id/96574/4/04%20BAB%203.pdf
document_url: http://repository.mercubuana.ac.id/96574/5/05%20BAB%204.pdf
document_url: http://repository.mercubuana.ac.id/96574/6/06%20BAB%205.pdf
document_url: http://repository.mercubuana.ac.id/96574/7/07%20DAFTAR%20PUSTAKA.pdf
document_url: http://repository.mercubuana.ac.id/96574/8/08%20LAMPIRAN.pdf