Prediksi Stunting Menggunakan Random Forest dan SMOTE Berdasarkan Data Posyandu

Selvi Nuriana; Fitri Yunita

doi:10.31004/riggs.v5i2.12624

Authors

Selvi Nuriana Universitas Islam Indragiri
Fitri Yunita Universitas Islam Indragiri

DOI:

https://doi.org/10.31004/riggs.v5i2.12624

Keywords:

Stunting, Random Forest, SMOTE, Machine Learning, Prediksi Stunting, Posyandu

Abstract

Stunting merupakan salah satu permasalahan kesehatan yang masih menjadi perhatian di Indonesia karena dapat memengaruhi pertumbuhan fisik, perkembangan kognitif, dan kualitas sumber daya manusia di masa mendatang. Penelitian ini bertujuan membangun model prediksi status stunting pada balita menggunakan algoritma Random Forest serta menganalisis pengaruh penerapan Synthetic Minority Oversampling Technique (SMOTE) terhadap performa model. Dataset yang digunakan merupakan data primer yang berasal dari 24 Posyandu di wilayah kerja Puskesmas Gajah Mada dengan jumlah data akhir sebanyak 1.330 balita yang terdiri atas 1.287 balita tidak stunting dan 43 balita stunting. Tahap penelitian meliputi preprocessing data, pembentukan variabel target, train-test split, penerapan SMOTE, pembangunan model Random Forest, dan evaluasi model menggunakan accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model Random Forest tanpa SMOTE menghasilkan accuracy sebesar 96,99%, precision sebesar 100%, recall sebesar 11,11%, dan F1-score sebesar 20%. Setelah penerapan SMOTE, performa model meningkat dengan accuracy sebesar 97,37%, precision sebesar 75%, recall sebesar 33,33%, dan F1-score sebesar 46,15%. Hasil tersebut menunjukkan bahwa SMOTE mampu meningkatkan kemampuan model dalam mendeteksi kasus stunting. Penelitian ini diharapkan dapat membantu kader Posyandu, tenaga kesehatan, Puskesmas, pemerintah daerah, dan pengelola Program Makan Bergizi Gratis dalam melakukan identifikasi dini balita yang berisiko mengalami stunting.

Downloads

Download data is not yet available.

References

[1] World Health Organization, “Child Growth.” [Online]. Available: https://www.who.int/health-topics/child-growth

[2] United Nations Children’s Fund, “Child Nutrition.” [Online]. Available: https://data.unicef.org/nutrition

[3] Kementerian Kesehatan Republik Indonesia, “Survei Kesehatan Indonesia (SKI) 2023,” Jakarta, 2024. [Online]. Available: https://www.badankebijakan.kemkes.go.id/hasil-ski-2023

[4] Kementerian Kesehatan Republik Indonesia, “Hasil Survei Status Gizi Indonesia (SSGI) 2022,” Jakarta, 2023. [Online]. Available: https://ayosehat.kemkes.go.id/publikasi-hasil-survei-status-gizi-indonesia-ssgi-2022

[5] W. R. Mgomezulu, P. Thangata, B. Mkandawire, and N. Amoah, “Advancing predictive analytics in child malnutrition: Machine, ensemble and deep learning models with balanced class distribution for early detection of stunting and wasting,” Hum. Nutr. Metab., vol. 42, no. August, p. 200340, 2025, doi: 10.1016/j.hnm.2025.200340.

[6] R. Kumar et al., “A comprehensive review of machine learning for heart disease prediction: challenges, trends, ethical considerations, and future directions,” Front. Artif. Intell., vol. 8, no. May, pp. 1–31, 2025, doi: 10.3389/frai.2025.1583459.

[7] A. H. Mubarok, P. Pujiono, D. Setiawan, D. F. Wicaksono, and E. Rimawati, “Parameter Testing on Random Forest Algorithm for Stunting Prediction,” Sinkron, vol. 9, no. 1, pp. 107–116, 2025, doi: 10.33395/sinkron.v9i1.14264.

[8] M. I. Elim and E. Utami, “Performance Comparison of Child Stunting Prediction Support Vector Machine vs Random Forest with Grid Search Optimization,” J. Tek. Inform., vol. 6, no. 5, pp. 5305–5319, 2025, doi: 10.52436/1.jutif.2025.6.5.5285.

[9] A. A. Dhani, T. A. Y. Siswa, and W. J. Pranoto, “Perbaikan Akurasi Random Forest Dengan ANOVA Dan SMOTE Pada Klasifikasi Data Stunting,” Teknika, vol. 13, no. 2, pp. 264–272, 2024, doi: 10.34148/teknika.v13i2.875.

[10] R. Belferik, F. M. Sinaga, F. Ferawaty, M. A. S. Manullang, and T. Sinaga, “Addressing Class Imbalance in Stunting Classification Using SMOTE Enhanced Random Forest,” Sinkron, vol. 9, no. 4, pp. 2108–2116, 2025, doi: 10.33395/sinkron.v9i4.15349.

[11] W. S. Lestari, Y. M. Saragih, and Caroline, “Comparison of Deep Neural Networks and Random Forest Algorithms for Multiclass Stunting Prediction in Toddlers,” Teknika, vol. 13, no. 3, pp. 412–417, 2024, doi: 10.34148/teknika.v13i3.1063.

[12] S. B. D. Widyawati, P. Purwadi, and I. R. Yunita, “Comparative Analysis of Random Forest, Logistic Regression and SVM for Stunting Prediction Using Anthropometric Data,” J. Inf. Syst. Informatics, vol. 7, no. 4, pp. 4271–4293, 2025, doi: 10.63158/journalisi.v7i4.1387.

[13] J. Juwariyem, S. Sriyanto, S. Lestari, and C. Chairani, “Prediction of Stunting in Toddlers Using Bagging and Random Forest Algorithms,” Sinkron, vol. 8, no. 2, pp. 947–955, 2024, doi: 10.33395/sinkron.v8i2.13448.

[14] D. Azriani, D. Agustian, Y. Zuhairini, I. N. Yulita, and M. Dhamayanti, “Prediction models for stunting at 2-years-old from Indonesian newborn population,” BMC Pediatr., vol. 25, no. 1, 2025, doi: 10.1186/s12887-025-06096-4.

[15] S. N. Syafa Iswahyudi and R. Eka Putra, “Sistem Deteksi Stunting pada Balita Berbasis Web Menggunakan Metode Random Forest,” J. Informatics Comput. Sci., vol. 6, no. 03, pp. 755–764, 2025, doi: 10.26740/jinacs.v6n03.p755-764.

[16] E. Miranda, M. Aryuni, A. Y. Zakiyyah, Y. E. Kurniawati, A. V. D. Sano, and M. Kumbangsila, “An early prediction model for toddler nutrition based on machine learning from imbalanced data,” Procedia Comput. Sci., vol. 245, pp. 263–271, 2024, doi: 10.1016/j.procs.2024.10.251.

[17] T. Sugihartono, D. Soetarno, and R. Sulaiman, “Ensemble Learning for Pediatric Stunting Detection : A Comparative Study of XGBoost , Random Forest , and LightGBM with Oversampling Techniques,” J. Inf. Syst. Informatics, vol. 8, no. 2, pp. 1672–1692, 2026.

[18] N. El Furqany, M. Subianto, and A. Rusyana, “Hybrid Ensemble Learning with SMOTEENN and Soft Voting for Stunting Risk Prediction: A SHAP-Based Explainable Approach,” J. Appl. Data Sci., vol. 6, no. 4, pp. 2989–3004, 2025, doi: 10.47738/jads.v6i4.829.

[19] B. Rao, M. G. Hasan, B. Putturaya, A. Kamath, M. Aatif, and Y. M. Elmosaad, “Multidimensional Correlates of Childhood Stunting in India: A Spatial Machine Learning and Explainable AI Approach,” Stats, vol. 9, no. 2, pp. 1–16, 2026, doi: 10.3390/stats9020034.

[20] M. M. Islam, N. M. Shoukot Jahan Kibria, S. Kumar, D. C. Roy, and M. R. Karim, “Prediction of undernutrition and identification of its influencing predictors among under-five children in Bangladesh using explainable machine learning algorithms,” PLoS One, vol. 19, no. 12, pp. 1–22, 2024, doi: 10.1371/journal.pone.0315393.