Prediksi Tingkat Obesitas Menggunakan Logistic Regression Dan Xgboost Berbasis Faktor Gaya Hidup Dan Antropometri

Indah Theresia Sibuea; Delima Sitanggang; Jamaluddin Hutajulu

doi:10.35960/ikomti.v7i2.2437

Authors

Indah Theresia Sibuea Universitas Prima Indonesia
Delima Sitanggang Program Studi Sistem Informasi, Sains dan Teknologi, Universitas Prima Indonesia
Jamaluddin Hutajulu Program Studi Sistem Informasi, Sains dan Teknologi, Universitas Prima Indonesia

DOI:

https://doi.org/10.35960/ikomti.v7i2.2437

Keywords:

Obesitas, Machine Learning, Logistic Regression, XGBoost, Prediksi

Abstract

Obesity is a growing health problem that can be influenced by various factors, such as diet, physical activity, and anthropometric conditions. This study aimed to predict obesity levels based on lifestyle and anthropometric factors using machine learning methods, namely Logistic Regression and XGBoost. The dataset used was obtained from the Kaggle platform, with a total of 2,111 data points and 17 attributes. The research process began with data preprocessing (label encoding and standard scaler), train-test data split (80:20), and validation using 5-Fold Stratified Cross-Validation. The results showed that the Logistic Regression model achieved 87.47% accuracy, while the XGBoost model achieved 95.98% accuracy in the train-test split and 94.35% ± 1.67% in the 5-Fold Cross-Validation. Feature importance analysis showed that Weight, Height, family_history_with_overweight, FAVC, and FAF were the most dominant predictors. Based on this comparison, the XGBoost model showed better performance and is recommended for predicting obesity levels.

References

[1] Gómez-Ambrosi, J., (2023), “Recent progress in the management of obesity”, Nutrients, Vol. 15, No. 12, Art. no. 2651.

[2] Moschonis, G., dan Trakman, G. L., (2023), “Overweight and obesity: The interplay of eating habits and physical activity”, Nutrients, Vol. 15, No. 13, Art. no. 2896.

[3] Ganie, S. M., Pramanik, P. K. D., dan Zhao, Z., (2025), “Lifestyle data-based multiclass obesity prediction with interpretable ensemble models incorporating SHAP and LIME analysis”, Scientific Reports, Vol. 15, Art. no. 36916.

[4] Barus, E. S., Zarlis, M., dan Nasution, Z., (2025), Development of Machine Learning for Forecasting Optimization Implemented in Morphology Plant Growth, Eastern-European Journal of Enterprise Technologies, Vol. 135 No. 2.

[5] Wong, J. E., Yamaguchi, M., Nishi, N., Araki, M., dan Wee, L. H., (2022), “Predicting overweight and obesity status among Malaysian working adults with machine learning or logistic regression: Retrospective comparison study”, JMIR Formative Research, Vol. 6, No. 12, p. e40404.

[6] Du, J., Yang, S., Zeng, Y., Ye, C., Chang, X., dan Wu, S., (2024), “Visualization obesity risk prediction system based on machine learning”, Scientific Reports, Vol. 14, Art. no. 22424.

[7] Tahapary, D. L., (2024), “Tackling obesity in Indonesia: Current problems and future directions”, Medical Journal of Indonesia, Vol. 33, No. 2, pp. 61–62.

[8] Sulistya, Y. I., dan Istighosah, M., (2025), “Obesity prediction with machine learning models comparing various algorithm performances”, International Journal of Artificial Intelligence in Medical Issues, Vol. 3, No. 1, pp. 1–15.

[9] Setiyani, L., Indahsari, A. N., dan Roestam, R., (2025), “Analisis prediksi level obesitas menggunakan perbandingan algoritma machine learning dan deep learning”, JTERA: Jurnal Teknologi Rekayasa.

[10] Airlangga, G., (2025), “A comparative analysis of machine learning models for obesity prediction”, Jurnal Informatika Ekonomi Bisnis, Vol. 7, No. 1, pp. 1–5.

[11] Widyastuti, T., Turner, R. M., Harcombe, H., dan McLean, R., (2023), “Trends in BMI of Indonesian adults between 1993 and 2014: A longitudinal population-based study”, Public Health Nutrition, Vol. 26, pp. 1394–1402.

[12] Liu, P. et al., (2025), “Heterogeneity of obesity and its predictive factors”, Preprints.

[13] Zhang, L., Yuan, Y., Hu, Y., dan Liao, P., (2025), “Obesity risk prediction using logistic regression and XGBoost: A comparative study”, dalam Proc. 2nd Int. Conf. on Digital Society and Artificial Intelligence (DSAI 2025).

[14] Pinar, A., Yagin, F. H., dan Georgian, B., (2024), “Use of logistic regression method in predicting obesity levels with machine learning method”, Journal of Exercise Science & Physical Activity Reviews, Vol. 2, No. 1, pp. 104–113.

[15] Gozukara Bag, H. G., Yagin, F. H., Görmez, Y., Prieto González, P., Colak, C., Gülü, M., Badicu, G., dan Ardigò, L. P., (2023), “Estimation of obesity levels through the proposed predictive approach based on physical activity and nutritional habits”, Diagnostics (Basel), Vol. 13, No. 18, Art. no. 2949

[16] Zhang, J. Y., (2025), “Machine learning analysis of obesity levels based on lifestyle and physical features”, Theoretical and Natural Science.

[17] Kumar, E., dan Sharma, N., (2025), “A micro-macro machine learning framework for predicting childhood obesity risk using NHANES and environmental determinants”, arXiv.

[18] Iqbal, M., Lisnawanty, W. S. D., dan Dharmawan, R. S., (2024), “Prediction of obesity categories based on physical activity using machine learning algorithms”, ResearchGate.

[19] Alpiansah, A. B., dan Ramdhani, Y., (2023), “Optimasi fitur dengan forward selection pada estimasi tingkat obesitas menggunakan random forest”, Sistemasi: Jurnal Sistem Informasi, Vol. 12, No. 3.

[20] Prediksi fluktuasi berat badan berdasarkan pola hidup menggunakan XGBoost dan deep learning”, Jurnal Algoritma, Vol. 22, No. 1, pp. 221–233.