Analisis Faktor Penentu Tingkat Obesitas Berdasarkan Feature Importance pada Random Forest

Muhammad Fauzan Rifnandy

doi:10.61132/neptunus.v4i2.1708

Authors

Muhammad Fauzan Rifnandy Universitas Islam Negeri Sumatera Utara

DOI:

https://doi.org/10.61132/neptunus.v4i2.1708

Keywords:

Age, Feature Importance, Obesity Classification, Random Forest, Weight

Abstract

Obesity is a growing health concern that is closely associated with various chronic diseases. Machine learning has been widely applied to classify obesity levels, yet most studies focus on improving predictive performance rather than identifying the features contributing to classification outcomes. This study aims to analyze the determining factors of obesity levels using Feature Importance in a Random Forest model. The research utilized the Estimation of Obesity Levels Based on Eating Habits and Physical Condition dataset from the UCI Machine Learning Repository. After preprocessing, 2,087 records were analyzed. Hyperparameter tuning was performed using GridSearchCV, and model performance was evaluated using Accuracy, Precision, Recall, and F1-Score. The optimized Random Forest achieved an Accuracy of 94.26%, Precision of 94.60%, Recall of 94.26%, and F1-Score of 94.34%. Feature Importance analysis identified Weight as the most influential feature, followed by Age, FCVC, Height, and Gender. The results demonstrate that Random Forest not only provides high classification performance but also helps identify the features that contribute most to obesity level classification.

References

Alfarisi, M. A., Sumanto, B., & Putu, F. R. (2025). Pengembangan Model Machine Learning untuk Deteksi Penyakit Diabetes Menggunakan Analisis Gini Importance. Journal of Internet and Software Engineering, 127-134.

Andhika, A. R., & Bayunanda, E. (2025). Studi Literature Review Pemanfaatan Machine Learning Dalam Multisektor. Integrative Perspectives of Social and Science Journal, 6865-6880.

Daka, R., Martha, E., & Putu, L. (2025). Faktor-Faktor Yang Mempengaruhi Kejadian Obesitas Pada Remaja Di Indonesia. Jurnal NERS, 3190-3205.

Ernawati, A., Sitorus, Z., Iqbal, M., & Nasution, D. (2025). Penerapan Data Mining Untuk Klasifikasi Penduduk Miskin Di Kabupaten Labuhanbatu Menggunakan Random Forest Dan K-Nearest Neighbors. Bulletin of Information Technology (BIT), 23-35.

Felndity, B., Sahsun, D., Saiful, S., Musa, S., & Lestari, T. (2025). Upaya Pencegahan Obesitas Pada Remaja Melalui Pendidikan Kesehatan. Indonesian Journal of Community Empowerment, 653-659.

Fitria, D. A., & Fitria, D. A. (2019). Hubungan Obesitas Terhadap Keseimbangan Postural. JIMKI, 76-89.

Fitriani, S., Budiman, E., & Fadli, M. (2025). Optimalisasi Metode Random Forest menggunakan Particle Swarm Optimization dalam Prediksi Prestasi Mahasiswa. Prosiding Seminar Nasional Teknologi Komputer dan Sains, 406-415.

Handyanto, L., Arifin, W. A., & Syafri, H. (2026). Perbandingan Metode Hyperparameter Tuning Pada Model XGBoost Untuk Prediksi Multioutput. JURTI, 50-59.

Haris, M., Anam, K., & Kurnianingtyas, D. (2026). Implementasi Algoritma Random Forest Untuk Prediksi Churn Pada Pelanggan Retail Online. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 1-10.

Ismail, M. Y., & Atim, S. B. (2025). Klasifikasi Level Obesitas Menggunakan Decision Tree C45 Dalam Menentukan Akurasi Pada Kriteria Information Gain, Gain Ratio, Gini Index. JIKI, 169-178.

Juliani, E., & Voutama, A. (2025). Optimasi Algoritma Random Forest Untuk Meningkatkan Akurasi Prediksi Indeks Massa Tubuh (Bmi). JuSIN, 11-20.

Kemenkes. (2024). Sering Dianggap Menggemaskan, Obesitas Membahayakan Masa Depan Anak. Retrieved from kemkes.go.id: https://kemkes.go.id/id/sering-dianggap-menggemaskan-obesitas-membahayakan-masa-depan-anak

Pandu, M. A., Saputro, R. E., & Purwadi, P. (2025). Analisis Tingkat Akurasi Metode Naive Bayes dan Random Forest dalam Prediksi Penjualan Emas. Jurnal Pendidikan dan Teknologi Indonesia, 1809-1821.

Saputri, I., Arsi, P., & Isnaini, K. N. (2025). Effectiveness Hyperparameter Tuning On Random Forest, Linear Discriminant Analysis, Logistic Regression And Naïve Bayes Algorithms For Detecting Dos Network Attacks. Jurnal Teknik Informatika, 87-104.

Utiarahman, S. A., Mulawati, A., & Pratama, M. (2024). Penerapan Support Vector Machine dan Random Forest Classifier Untuk Klasifikasi Tingkat Obesitas. Jurnal FASILKOM, 754-760.

Valerian, F. R., Syarief, M., & Fatah, D. A. (2025). Klasifikasi Tingkat Obesitas Menggunakan Metode Gbm Dan Confusion Matrix. JATI, 2242-2249.

Wahyudi, A., Al Baihaqi, M. A., & Febrinanda, I. V. (2025). Penerapan Random Forest untuk Klasifikasi Risiko Penyakit Stroke Pada Rentang Usia 40-85 Tahun. JUKOMIKA, 118-124.

Wardhana, R. G., Wang, G., & Sibuea, F. (2023). Penerapan Machine Learning Dalam Prediksi Tingkat Kasus Penyakit Di Indonesia. JOISM, 40-45.

WHO. (2025). Obesity and Overweight. Retrieved from who.int: https://www.who.int/news-room/fact-sheets/detail/obesity-and-overweight