Comparative Evaluation of Machine Learning Algorithms Using SMOTENC in Classifying Toddler Nutritional Status Based on Anthropometric Data

  • ERIP SURATNO Universitas Nusa Putra ORCID
  • Adhi Kusnadi UNIVERSITAS NUSA PUTRA
  • Zeldi Suryady UNIVERSITAS NUSA PUTRA
PDF
DOI https://doi.org/10.31544/jtera.v11.i1.2026.101-110
Published 2026-06-26
Full Text Preview
Download PDF

Abstract

Class imbalance in under-five nutritional status data can make classification models appear accurate while limiting minority-class recognition. This study evaluated Support Vector Machine, K-Nearest Neighbors, Naive Bayes, Decision Tree, and Random Forest for multiclass classification of under-five nutritional status using anthropometric data. The dataset contained 3,716 Posyandu Desa Ujunggenteng records from 2025, with sex, age, weight, and height as features and four target classes: undernutrition, good nutritional status, risk of overnutrition, and overnutrition. Labels were treated as operational records, not as recalculated WHO/Indonesian Ministry of Health z-score standards. The experiment used an 80:20 stratified train-test split, 5-fold Stratified K-Fold Cross-Validation, limited candidate-based parameter search, numerical-categorical preprocessing, and SMOTENC only on training data or training folds. Cross-validation showed that SVM achieved the highest CV Macro F1-score of 0.829578. On the test set, Random Forest obtained the highest Macro F1-score of 0.827132, while KNN achieved the highest accuracy of 0.956989 and balanced accuracy of 0.883393. Model selection should consider Macro F1-score, balanced accuracy, confusion matrix, and class-wise performance. Based on cross-validation, SVM was selected as the final model, while Random Forest was reported as the best test-set model based on Macro F1-score.

References

P. Mendon, M. Witsch, M. Becker, A. Adamski, and M. Vaillant, “Facilitating comprehensive child health monitoring within REDCap - an open-source code for real-time Z-score assessments,” BMC Med. Res. Methodol., vol. 24, no. 1, 2024, doi: 10.1186/s12874-024-02405-0.
[2] R. Oliveira-Santos et al., “Composite anthropometric data quality index for children under the age of 5 on the Brazilian National Food and Nutrition Surveillance System, 2019–2021,” Popul. Health Metr., vol. 23, no. 1, 2025, doi: 10.1186/s12963-025-00371-3.
[3] F. H. Bitew, C. S. Sparks, and S. H. Nyarko, “Machine learning algorithms for predicting undernutrition among under-five children in Ethiopia,” Public Health Nutr., vol. 25, no. 2, pp. 269–280, 2022, doi: 10.1017/S1368980021004262.
[4] O. N. Chilyabanyama et al., “Performance of Machine Learning Classifiers in Classifying Stunting among Under-Five Children in Zambia,” Children, vol. 9, no. 7, 2022, doi: 10.3390/children9071082.
[5] S. Ndagijimana, I. H. Kabano, E. Masabo, and J. M. Ntaganda, “Prediction of Stunting among Under-5 Children in Rwanda Using Machine Learning Techniques,” J. Prev. Med. Public Heal., vol. 56, no. 1, pp. 41–49, 2023, doi: 10.3961/jpmph.22.388.
[6] N. Novalina, I. A. A. Tarigan, F. K. Kameela, and M. Rizkinia, “Benchmarking machine learning algorithm for stunting risk prediction in Indonesia,” Bull. Electr. Eng. Informatics, vol. 14, no. 3, pp. 2252–2263, 2025, doi: 10.11591/eei.v14i3.8997.
[7] M. K. Ayele, G. A. Baye, S. H. Yesuf, A. A. Engda, and E. T. Mitiku, “Predicting stunting status among under five children in ethiopia using ensemblemachine learning algorithms,” Sci. Rep., vol. 15, no. 1, pp. 1–11, 2025, doi: 10.1038/s41598-025-03206-1.
[8] M. N. A. Khan and R. M. Yunus, “A hybrid ensemble approach to accelerate the classification accuracy for predicting malnutrition among under-five children in sub-Saharan African countries,” Nutrition, vol. 108, p. 111947, 2023, doi: https://doi.org/10.1016/j.nut.2022.111947.
[9] 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.
[10] G. B. Begashaw, T. Zewotir, and H. M. Fenta, “A deep learning approach for classifying and predicting children’s nutritional status in Ethiopia using LSTM-FC neural networks,” BioData Min., vol. 18, no. 1, 2025, doi: 10.1186/s13040-025-00425-0.
[11] E. K. Anku and H. O. Duah, “Predicting and identifying factors associated with undernutrition among children under five years in Ghana using machine learning algorithms,” PLoS One, vol. 19, no. 2 February, pp. 1–16, 2024, doi: 10.1371/journal.pone.0296625.
[12] S. Wang, Y. Dai, J. Shen, and J. Xuan, “Research on expansion and classification of imbalanced data based on SMOTE algorithm,” Sci. Rep., vol. 11, no. 1, pp. 1–11, 2021, doi: 10.1038/s41598-021-03430-5.
[13] J. Li, Q. Zhu, Q. Wu, and Z. Fan, “A novel oversampling technique for class-imbalanced learning based on SMOTE and natural neighbors,” Inf. Sci. (Ny)., vol. 565, pp. 438–455, 2021, doi: https://doi.org/10.1016/j.ins.2021.03.041.
[14] 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.
[15] R. Gustriansyah, N. Suhandi, S. Puspasari, and A. Sanmorino, “Machine Learning Method to Predict the Toddlers’ Nutritional Status,” J. Infotel, vol. 16, no. 1, pp. 32–43, 2024, doi: 10.20895/infotel.v15i4.988.
[16] A. Subekti, “Comparative Analysis of Automated Machine Learning Methods for Multiclass Stunting Prediction Using Anthropometric Data,” vol. 10, no. 2, pp. 991–1002, 2026, doi: 10.33395/sinkron.v10i2.15886.

Issue

Vol. 11 No. 1: June 2026

Section

Articles

License

Creative Commons License

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

Authors who publish with this journal agree to the following terms:

The copyright to this article is transferred to JTERA if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to JTERA. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment. The copyright transfer form will be sent via email before the article published.

The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.

How to Cite

[1]
“Comparative Evaluation of Machine Learning Algorithms Using SMOTENC in Classifying Toddler Nutritional Status Based on Anthropometric Data”, JTERA, vol. 11, no. 1, pp. 101–110, Jun. 2026, doi: 10.31544/jtera.v11.i1.2026.101-110.