IMPLEMENTASI ALGORITMA RANDOM FOREST DALAM MENDIAGNOSA STUNTING PADA ANAK DAN BALITA DI PUSKESMAS MAJA DENGAN TEKNIK SMOTE

Retno Dwi Cahyani, . (2025) IMPLEMENTASI ALGORITMA RANDOM FOREST DALAM MENDIAGNOSA STUNTING PADA ANAK DAN BALITA DI PUSKESMAS MAJA DENGAN TEKNIK SMOTE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (253kB)
[img] Text
AWAL.pdf
Download (575kB)
[img] Text
BAB I.pdf
Download (298kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (704kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (757kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB V.pdf
Download (273kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (278kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (128kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (752kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (20MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (739kB)

Abstract

Stunting is a chronic health issue that affects the growth and development of children and toddlers. In this study, the Maja Health Center area continues to report a relatively high prevalence of stunting cases. This research aims to diagnose stunting and identify high-risk areas by implementing the Random Forest algorithm, combined with the SMOTE technique and its variation, SMOTE-Tomek Links, to address data imbalance. A total of 16,515 data records from 2022 to 2024 were used. The process includes data preprocessing, model training, and evaluation using accuracy, precision, recall, F1-score, and AUC metrics. Among the three tested scenarios, the Random Forest model with SMOTE-Tomek Links was selected as the best-performing model, achieving balanced results with 90.21% accuracy, 37.63% precision, 79.87% recall, 51.16% F1-score, and 93.12% AUC. The model is also implemented in a Streamlit-based GUI application to facilitate stunting prediction and visualization of high-risk areas. This system is expected to assist healthcare workers in early and accurate stunting detection.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110511103] [Pembimbing 1: Widya Cholil] [Pembimbing 2: Neny Rosmawarni] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: Nurul Afifah Arifuddin]
Uncontrolled Keywords: Diagnosis, Random Forest, SMOTE, SMOTE-Tomek Links, Stunting
Subjects: Q Science > Q Science (General)
Q Science > QA Mathematics
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: RETNO DWI CAHYANI
Date Deposited: 13 Jul 2025 21:24
Last Modified: 13 Jul 2025 21:24
URI: http://repository.upnvj.ac.id/id/eprint/37458

Actions (login required)

View Item View Item