Catboost Modeling In The Classification Of Factors Influencing Nutritional Status In Toddlers

Muhammad Amin, Fadhillah Fitri

Abstract


Childhood malnutrition remains a major public health challenge in Indonesia due to the complex interactions among maternal, socioeconomic, and demographic factors influencing nutritional status. This study aimed to develop a CatBoost-based classification model to identify the determinants of nutritional status among children under five in West Sumatra, Indonesia. A quantitative predictive research design was employed using secondary survey data. Data preprocessing included cleaning, handling missing values, feature selection, and partitioning the dataset into training and testing subsets. The CatBoost classifier was trained through hyperparameter optimization and evaluated using accuracy, precision, recall, F1-score, confusion matrix, and receiver operating characteristic (ROC) analysis. The optimal model was obtained with a tree depth of four and 400 boosting iterations, achieving an accuracy of 45% and a Macro F1-score of 0.4282. Feature importance analysis identified maternal nutritional knowledge as the most influential predictor, followed by maternal education, household per-capita income, maternal employment status, and maternal age. These findings demonstrate that CatBoost is a promising machine learning approach for identifying key determinants of childhood nutritional status and can support evidence-based nutritional surveillance and targeted public health interventions.

Keywords


Chatboost, Child Nutritional Status, Predictive Modeling, West Sumatera.

Full Text:

PDF

References


P. R. Indonesia., “Undang-Undang Republik Indonesia Nomor 59 Tahun 2024 tentang Rencana Pembangunan Jangka Panjang Nasional Tahun 2025–2045,” https://jdih, 2024.

S. W. P. R. Indonesia., “Strategi Nasional Percepatan Pencegahan dan Penurunan Stunting 2025–2029,” https://stunting, 2024.

M. B. Ali, R. Tuhin, M. A. Alim, M. Rokonuzzaman, S. M. Rahman, and M. Nuruzzaman, “Acceptance and use of ICT in tourism: the modified UTAUT model,” J. Tour. Futur., vol. 10, no. 2, pp. 334–349, 2024, doi: 10.1108/JTF-06-2021-0137.

World Health Organization, “Malnutrition,” 2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/malnutrition/

A. T. Abeng, D. Ismail, and E. Huriyati, “Sanitasi, infeksi, dan status gizi anak balita di Kecamatan Tenggarong Kabupaten Kutai Kartanegara,” J. Gizi Klin. Indones., vol. 10, no. 3, p. 159, 2014, doi: 10.22146/ijcn.18867.

E. Suminar and A. R. Wibowo, “The Correlation Between Infection Diseases History and Nutritional Status in Toddler,” Fundam. Manag. Nurs. J., vol. 4, no. 1, p. 18, 2021, doi: 10.20473/fmnj.v4i1.21587.

Kemenkes RI, “Hasil Survei Status Gizi Indonesia (SSGI) 2022,” Kemenkes, pp. 1–150, 2022.

WHO., “Physical status: The use and interpretation of anthropometry,” WHO Tech. Rep. Ser. No, 1995.

L. A. Budiman Rosiyana, R., Sari, A. S., Safitri, S. J., Prasetyo, R. D., Rizqina, H. A., Neng I Kasim, I. S., & Indriany Korwa, V. M., “Analisis Status Gizi Menggunakan Pengukuran Indeks Massa Tubuh dan Beban Kerja dengan Metode 10 Denyut pada Tenaga Kesehatan,” Nutr. Nutr. Res. Dev. J., 2021.

I. S. Paramita, H. Atasasih, and D. Rahayu, Penilaian Status Gizi Antropometri Pada Balita, 1st ed. CV. Sarana Ilmu Indonesia, 2024.

F. K. Lailani, Yuliana, and A. Yulastri, “Literature Riview : Masalah Terkait Malnutrisi: Penyebab, Akibat, dan Penanggulangannya,” JGK J. Gizi dan Kesehat., vol. 2, no. 2, pp. 129–138, 2022, doi: 10.36086/jgk.v2i2.1503.

N. E. Rosuliana, T. Nurhayati, E. Mawaddah, and M. U. Ningsih, Buku saku deteksi dini dan perawatan balita pneumonia. Cipedes: Perkumpulan Rumah Cemerlang Indonesia ANGGOTA IKAPI JAWA BARAT Pondok, 2024.

A. A. Reddy et al., “Perspectives on Forest governance among the indigenous communities of India’s Eastern Ghats,” For. Policy Econ., vol. 169, p. 103350, 2024, doi: https://doi.org/10.1016/j.forpol.2024.103350.

R. Hidayat Mahdiana, D., & Fergina, A., “Comparative Analysis of Logistic Regression, SVM, Xgboost, and Random Forest Algorithms for Diabetes Classification,” J. Teknol. Sist. Inf. Dan Apl., 2024.

S. Ramadhani & Wayahdi, M. R., “K-Nearest Neighbor and Random Forest Algorithms in Loan Approval Prediction,” J. Minfo Polgan, 2024.

Y. F. Zamzam Saragih, T. H., Herteno, R., Muliadi, Nugrahadi, D. T., & Huynh, P.-H., “Comparison of Catboost and Random Forest Methods for Lung Cancer Classification using Hyperparameter Tuning Bayesian Optimization-based,” J. Electron., 2024.

L. Prokhorenkova Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A., “Catboost: Unbiased boosting with categorical features,” 32nd Conf. Neural Inf. Process. Syst., 2018.

J. T. Hancock & Khoshgoftaar, T. M., “Catboost for big data: An interdisciplinary review,” J. Big Data, 2020.

A. Maulana Afidh, R. P. F., Maulydia, N. B., Idroes, G. M., & Rahimah, S., “Predicting Obesity Levels with High Accuracy: Insights from a Catboost Machine Learning Model,” Infolitika J. Data Sci., 2024.

S. S. M. Alqrinawi Burhanuddin, M. A., & Salahuddin, L., “Catboost Model for Enhanced Treatment Prediction in Type 2 Diabetes Patients,” J. Inf. Syst. Eng. Manag., 2025.

Y. Zhang Zhang, H., Wang, D., Li, N., Lv, H., & Zhang, G., “Development of a 5-Year Risk Prediction Model for Transition From Prediabetes to Diabetes Using Machine Learning: Retrospective Cohort Study,” J. Med. Internet Res., 2025.

B. Mutonhodza, M. G. Manzeke-Kangara, E. H. Bailey, T. M. Matsungo, and P. Chopera, “Maternal selenium deficiency was positively associated with the risk of selenium deficiency in children aged 6–59 months in rural Zimbabwe,” PLOS Glob. Public Heal., vol. 4, no. 7, p. e0003376, 2024, doi: 10.1371/journal.pgph.0003376.

D. T. Wilujeng Fatekurohman, M., & Tirta, I. M., “Analisis Risiko Kredit Perbankan Menggunakan Algoritma K-Nearest Neighbor dan Nearest Weighted K-Nearest Neighbor,” Indones. J. Appl. Stat., 2023.




DOI: http://dx.doi.org/10.52155/ijpsat.v58.2.8485

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Muhammad Amin

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.