OPTIMASI ALGORITMA RANDOM FOREST UNTUK MENINGKATKAN AKURASI PREDIKSI INDEKS MASSA TUBUH (BMI)
Dublin Core
Title
OPTIMASI ALGORITMA RANDOM FOREST UNTUK MENINGKATKAN AKURASI PREDIKSI INDEKS MASSA TUBUH (BMI)
Subject
Body Mass Index, Random Forest, Machine Learning
Description
Accurate Body Mass Index (BMI) prediction is essential for detecting obesity risks and related diseases.
This study optimizes the Random Forest algorithm to enhance BMI prediction accuracy through
hyperparameter tuning and feature selection. The dataset used is Obesity: Raw and Synthetic Data, which
includes demographic and lifestyle variables. After undergoing subsetting, label encoding, and data
imbalance handling using SMOTE, the model was trained using Random Forest and evaluated with
accuracy, precision, recall, and F1-score metrics. The results indicate that the optimized model achieved
90% accuracy, with precision and recall of 0.89. Additionally, the feature importance analysis identified
weight, height, and dietary habits as the most influential factors in BMI prediction. These findings confirm
that optimizing the algorithm enhances model reliability in BMI classification and can be applied in datadriven health monitoring systems. This research is expected to contribute to the development of digital health applications and more accurate early obesity detection systems.
This study optimizes the Random Forest algorithm to enhance BMI prediction accuracy through
hyperparameter tuning and feature selection. The dataset used is Obesity: Raw and Synthetic Data, which
includes demographic and lifestyle variables. After undergoing subsetting, label encoding, and data
imbalance handling using SMOTE, the model was trained using Random Forest and evaluated with
accuracy, precision, recall, and F1-score metrics. The results indicate that the optimized model achieved
90% accuracy, with precision and recall of 0.89. Additionally, the feature importance analysis identified
weight, height, and dietary habits as the most influential factors in BMI prediction. These findings confirm
that optimizing the algorithm enhances model reliability in BMI classification and can be applied in datadriven health monitoring systems. This research is expected to contribute to the development of digital health applications and more accurate early obesity detection systems.
Creator
Eva Juliani, Apriade Voutama
Source
https://ojs.itb-ad.ac.id/index.php/JUSIN/article/view/3021
Publisher
Institut Teknologi dan Bisnis Ahmad Dahlan.
Date
2025-06-25
Contributor
Sri Wahyuni
Rights
E-ISSN : 2797-8516
Format
PDF
Language
Indonesian
Type
Text
Files
Collection
Citation
Eva Juliani, Apriade Voutama, “OPTIMASI ALGORITMA RANDOM FOREST UNTUK MENINGKATKAN AKURASI PREDIKSI INDEKS MASSA TUBUH (BMI),” Repository Horizon University Indonesia, accessed January 12, 2026, https://repository.horizon.ac.id/items/show/10249.