Article Per Year (5 Year)
p-Index From 2020 - 2025
1.431
P-Index
This Author published in this journals
All Journal Jurnal Khatulistiwa Informatika Techno Nusa Mandiri : Journal of Computing and Information Technology Jurnal Serambi Engineering Jurnal Nasional Komputasi dan Teknologi Informasi Journal of Information System, Applied, Management, Accounting and Research JTIK (Jurnal Teknik Informatika Kaputama) Jurnal Sistem Informasi Bulletin of Computer Science Research Jurnal Esensi Infokom: Jurnal Esensi Sistem Informasi dan Sistem Komputer
Luci Kanti Rahayu
Universitas Bina Sarana Informatika
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Neuroscience Transportation

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Bulletin of Computer Science Research

 1 
Model Klasifikasi Risiko Stunting Pada Balita Menggunakan Algoritma CatBoost Classifier Pahlevi, Omar; Wulandari, Dewi Ayu Nur; Rahayu , Luci Kanti; Leidiyana, Henny; Handrianto, Yopi
Bulletin of Computer Science Research Vol. 4 No. 6 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v4i6.373

Abstract

Stunting is a significant health issue in Indonesia, affecting the growth and development of young children and influenced by various complex risk factors such as nutrition, environment, and access to healthcare services. The manual process of identifying stunting risks often requires considerable time, resources, and specialized expertise from medical professionals. This study aims to develop a stunting risk classification model for young children using machine learning through the CatBoost Classifier algorithm. This algorithm was chosen for its advantages in handling categorical variables without requiring complex encoding processes and its ability to manage imbalanced data, ultimately improving prediction accuracy. In the conducted case study, the model's prediction updates were illustrated by increasing the initial prediction from 0.25 to 0.27 after accounting for residual corrections in the first iteration, with a learning rate of 0.1. This process demonstrates CatBoost's iterative mechanism for improving model predictions through gradual updates. Evaluation results showed that the developed model achieved an accuracy of 98.47% and a ROC-AUC score of 1.00 for several classes, indicating a high capability in accurately classifying stunting risks. These findings suggest that the CatBoost algorithm is effective for stunting risk classification, capable of handling data complexity, and expected to contribute significantly to supporting stunting prevention efforts through improved early detection.
Co-Authors Agustiena Merdekawati, Agustiena Ahmad Baroqah Pohan Azis Sukma Dhiana Dewi Ayu Nur Wulandari Dwi Cahyo Putra Emiliya, Devi Fajar Agustini Germanus Yosef Rugi Laka Hendra Permana Henny Leidiyana Jasmine Celia Sahfitri Linda Marlinda Martini Martini Muhammad Ali Nabilla, Rizki Omar Pahlevi Syabani, Khofifah Nur Wahid Fajar Wahyudi Wasis Zakaria Wida Prima Mustika Yahdi Kusnadi Yopi Handrianto, Yopi Yuni Fitriani, Yuni