Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Informatika
Andriyani, Reva
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparative Analysis of Naïve Bayes Variants for Predicting Stunting-Risk Families Muis, Alwas; Razilu, Zila; Senga, Umy Ramadhani; Wulandari, Hutri; Andriyani, Reva
Jurnal Informatika Vol. 13 No. 1 (2026): April
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/informatika.v13i1.11910

Abstract

Stunting is a chronic nutritional condition that adversely affects children’s physical growth and cognitive development, highlighting the need for effective early detection, particularly at the household level. This study proposes a comparative analysis of three Naïve Bayes variants Gaussian, Multinomial, and Bernoulli to identify families at risk of stunting using machine learning techniques. The dataset used in this study consists of family-level records obtained from the National Population and Family Planning Agency (BKKBN) of Southeast Sulawesi Province, comprising demographic, socioeconomic, and health-related attributes. Data preprocessing involved handling missing values, removing irrelevant attributes, and transforming categorical variables. The dataset was divided into training and testing sets using an 80:20 ratio. The main contribution of this study lies in evaluating the effectiveness of different Naïve Bayes variants for family-based stunting risk prediction, which has been rarely explored in previous studies. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results indicate that the Bernoulli Naïve Bayes model achieved the best performance, with an accuracy of 88% and balanced evaluation metrics across both classes. These findings suggest that the Bernoulli Naïve Bayes model is the most suitable approach for predicting family-level stunting risk and can support data-driven early intervention strategies.
Co-Authors Muis, Alwas Razilu, Zila Senga, Umy Ramadhani Wulandari, Hutri