Comparative Analysis of GridSearchCV and RandomSearchCV for LightGBM-Based Stunting Prediction Using (MICS6) Bangladesh 2019 Data

Fitri Mintarsih; Nisrina Nurani Anwar; Andrew Fiade; Victor Amrizal; Hendra Bayu Suseno

doi:10.15408/jti.v19i2.54321

Authors

Fitri Mintarsih Department of Informatics, Faculty of Science and Technology, Syarif Hidayatullah State Islamic University Jakarta, Indonesia
Nisrina Nurani Anwar Department of Informatics, Faculty of Science and Technology, Syarif Hidayatullah State Islamic University Jakarta, Indonesia
Andrew Fiade Department of Informatics, Faculty of Science and Technology, Syarif Hidayatullah State Islamic University Jakarta, Indonesia
Victor Amrizal Department of Informatics, Faculty of Science and Technology, Syarif Hidayatullah State Islamic University Jakarta, Indonesia
Hendra Bayu Suseno Department of Informatics, Faculty of Science and Technology, Syarif Hidayatullah State Islamic University Jakarta, Indonesia

DOI:

https://doi.org/10.15408/jti.v19i2.54321

Keywords:

LightGBM, Hyperparameter Tuning, GridSearchCV, RandomSearchCV, Stunting

Abstract

Stunting among children under five is a major public health concern that can impair physical growth and cognitive development. This study evaluates and compares GridSearchCV and RandomSearchCV for hyperparameter tuning of the LightGBM algorithm in predicting stunting using data from the Multiple Indicator Cluster Surveys (MICS6) Bangladesh 2019. The dataset comprises demographic and child health variables, and model performance was evaluated using training-to-testing ratios of 70:30, 80:20, and 90:10. Accuracy, precision, recall, F1-score, and execution time were used as evaluation metrics. The results showed that the 90:10 split yielded the best overall performance. Among the evaluated configurations, LightGBM with RandomSearchCV achieved an accuracy of 98.09%, precision of 95.93%, recall of 97.08%, and an F1-score of 96.50%, with a reported execution time of 0.1 seconds. Compared with the untuned model, hyperparameter tuning provided only marginal improvements in classification performance, while RandomSearchCV offered a favorable balance between predictive performance and computational efficiency. These findings demonstrate the potential of LightGBM-based stunting prediction using (MICS6) Bangladesh 2019 data. However, further evaluation using independent datasets is necessary to assess the model's generalizability and its potential application in early stunting detection.

References

[1] Yuliastri, N. (2024). From Womb to World: Immunological Pathways Influencing Stunting and 2030 Sustainability. RSF Conference Series: Business, Management and Social Sciences. https://doi.org/10.31098/bmss.v4i1.886.

[2] Kawo, M. A., Idris, M. N., Haruna, K., & Kaita, F. U. (2024). Predicting Undernutrition Risk Factors Using Machine Learning Techniques in Nigerian Under Five Children. International Journal of Computer Science and Mobile Computing, 13(7), 56–70. https://doi.org/10.47760/ijcsmc.2024.v13i07.006.

[3] Chowdhury, T. R., Chakrabarty, S., Rakib, M., Winn, S., & Bennie, J. (2022). Risk factors for child stunting in Bangladesh: an analysis using MICS 2019 data. Archives of Public Health, 80. https://doi.org/10.1186/s13690-022-00870-x.

[4] Ekka Pujo Ariesanto Akhmad. (2025). Enhancing the Accuracy of Airline Review Classification Using SMOTE and Grid Search with Cross Validation for Hyperparameter Tuning. Journal of Information Systems Engineering and Management, 10(25s), 850–861. https://doi.org/10.52783/jisem.v10i25s.4174.

[5] Hartanto, A. D., Kholik, Y. N., & Pristyanto, Y. (2023). Stock Price Time Series Data Forecasting Using the Light Gradient Boosting Machine (LightGBM) Model. International Journal on Informatics Visualization, 7(4), 2270–2279. https://doi.org/10.30630/joiv.7.4.1740.

[6] Intan, P. A., Ardhia, I. C., & Sri, C. K. A. (2024). Klasifikasi Penyakit Stunting Menggunakan Algoritma Multi-Layer Perceptron. Journal MIND Journal | ISSN, 9(1), 52–63. https://doi.org/10.26760/mindjournal.v9i1.52-63.

[7] Massari, H. El, Gherabi, N., Qanouni, F., & Mhammedi, S. (2024). Diabetes Prediction Using Machine Learning with Feature Engineering and Hyperparameter Tuning. 15(8), 171–179.

[8] Ndagijimana, S., Kabano, I., Masabo, E., & Ntaganda, J. (2023). Prediction of Stunting Among Under-5 Children in Rwanda Using Machine Learning Techniques. Journal of Preventive Medicine and Public Health, 56, 41–49. https://doi.org/10.3961/jpmph.22.388.

[9] Saarela, M., & Jauhiainen, S. (2021). Comparison of feature importance measures as explanations for classification models. SN Applied Sciences, 3. https://doi.org/10.1007/s42452-021-04148-9.

[10] Shao, H. Z., Liu, X., Zong, D. S., & Song, Q. J. (2024). Optimization of diabetes prediction methods based on combinatorial balancing algorithm. Nutrition and Diabetes, 14(1), 1–13. https://doi.org/10.1038/s41387-024-00324-z, doi: 10.12928/TELKOMNIKA.v12i4.537.

[11] Zhang, Y., Wang, C., Xia, Q., Jiang, W., Zhang, H., Amiri-Ardekani, E., Hua, H., & Cheng, Y. (2023). Machine learning-based prediction of candidate gene biomarkers correlated with immune infiltration in patients with idiopathic pulmonary fibrosis. Frontiers in Medicine, 10(February). https://doi.org/10.3389/fmed.2023.1001813.

[12] Khan, S., & Hancioglu, A. (2019). Multiple Indicator Cluster Surveys: Delivering Robust Data on Children and Women across the Globe. Studies in Family Planning, 50(3), 279–286. https://doi.org/10.1111/sifp.12103.

[13] Ji, Z., & Zhang, Y. (2022). Predictive Analysis of Cryptocurrency Residual Log-returns Based on LightGBM. Academic Journal of Business & Management, 4(4), 96–100. https://doi.org/10.25236/ajbm.2022.040419.

[14] Hastuti, N. T., & Budiman, F. (2024). Optimasi Klasifikasi Stunting Balita dengan Teknik Boosting pada Decision Tree. Edumatic: Jurnal Pendidikan Informatika, 8(2), 655–664. https://doi.org/10.29408/edumatic.v8i2.27913.

[15] Gujjar, J., & Kumar, V. (2021). Google Colaboratory : Tool for Deep Learning and Machine Learning Applications. International Journal in Computer Simulation, 6, 23–26. https://doi.org/10.17010/IJCS/2021/V6/I3-4/165408.

[16] Fajri, M., & Primajaya, A. (2023). Komparasi Teknik Hyperparameter Optimization pada SVM untuk Permasalahan Klasifikasi dengan Menggunakan Grid Search dan Random Search. Journal of Applied Informatics and Computing, 7(1), 14–19. https://doi.org/10.30871/jaic.v7i1.5004.

[17] Y. S. Deraman, I. Ahmad, A. F. Ramli, and N. A. M. Mortar, “Optimization performance of unmanned aerial vehicle in wireless sensor network,” AIP Conf. Proc., vol. 2291, no. November, 2020, doi: 10.1063/5.0025092.

[18] Bradshaw, T. J., Huemann, Z., Hu, J., & Rahmim, A. (2023). A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging. Radiology: Artificial Intelligence, 5(4). https://doi.org/10.1148/ryai.220232.

[19] Amin. (2022). Confusion Matrix in Binary Classification Problems: A Step-by-Step Tutorial. In Journal of Engineering Research. https://doi.org/10.21608/erjeng.2022.274526.

[20] Bairamova, D. (2024). Predicting Course Grades of Students Academic Performance Using The LightGBM Regressor. Suleyman Demirel University Bulletin Natural and Technical Sciences. https://doi.org/10.47344/sdubnts.v62i1.952.

[21] Ahamad, G. N., Shafiullah, Fatima, H., Imdadullah, Zakariya, S. M., Abbas, M., Alqahtani, M. S., & Usman, M. (2023). Influence of Optimal Hyperparameters on the Performance of Machine Learning Algorithms for Predicting Heart Disease. Processes, 11(3). https://doi.org/10.3390/pr11030734.

[22] Delgado-Panadero, Á., García-Ordás, M. T., & Benítez-Andrades, J. (2022). Implementing local-explainability in Gradient Boosting Trees: Feature Contribution. ArXiv, abs/2402.0. https://doi.org/10.1016/j.ins.2021.12.111.

[23] Khan, S., & Hancioglu, A. (2019). Multiple Indicator Cluster Surveys: Delivering Robust Data on Children and Women across the Globe. Studies in Family Planning, 50(3), 279–286. https://doi.org/10.1111/sifp.12103.

[24] Mohammed, A., & Kora, R. (2022). An effective ensemble deep learning framework for text classification. Journal of King Saud University - Computer and Information Sciences, 34(10), 8825–8837. https://doi.org/10.1016/j.jksuci.2021.11.001

[25] Nardkulpat, A., Boonpook, W., Sitthi, A., & Tan, Y. (2025). Machine learning-based and synthetic aperture radar time-series data for rice classification over Sentinel-1 imagery. Bulletin of Electrical Engineering and Informatics, 14(2), 1138–1150. https://doi.org/10.11591/eei.v14i2.7833

[26] Piegorsch, W. (2020). Confusion Matrix. Wiley StatsRef: Statistics Reference Online. https://doi.org/10.1002/9781118445112.stat08244.

[27] Ravichandran, T., Gavahi, K., Ponnambalam, K., Burtea, V., & Mousavi, S. J. (2021). leak detection in water mains. 307–323. https://doi.org/10.2166/hydro.2021.093.

[28] Ravichandran, T., Gavahi, K., Ponnambalam, K., Burtea, V., & Mousavi, S. J. (2021). leak detection in water mains. 307–323. https://doi.org/10.2166/hydro.2021.093

[29] Yan, J., Xu, Y., Cheng, Q., Jiang, S., Wang, Q., Xiao, Y., Ma, C., Yan, J., & Wang, X. (2021). LightGBM: accelerated genomically designed crop breeding through ensemble learning. Genome Biology, 22(1), 1–24. https://doi.org/10.1186/s13059-021-02492-y.

[30] Noor, M., Syarwani, M., Putri, R. M., Kalimantan, I., & Arsyad, M. (2024). Healthy Environment As A Human Right: Law Enforcement To Overcome Stunting In Children. At-Tadbir : Jurnal Ilmiah Manajemen. https://doi.org/10.31602/piuk.v0i0.15389,

[31] Deng, L., & Xiao, M. (2024). Hyperparameter recommendation via automated meta-feature selection embedded with kernel group Lasso learning. Knowl. Based Syst., 306, 112706. https://doi.org/10.1016/j.knosys.2024.112706.

[32] Hapsari, G. I., Munadi, R., Erfianto, B., & Irawati, I. D. (2025). Feature Selection Using Pearson Correlation for Ultra-Wideband Ranging Classification. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi). https://doi.org/10.29207/resti.v9i2.6281.

[33] Shao, H. Z., Liu, X., Zong, D. S., & Song, Q. J. (2024). Optimization of diabetes prediction methods based on combinatorial balancing algorithm. Nutrition and Diabetes, 14(1), 1–13. https://doi.org/10.1038/s41387-024-00324-z.

[34] S. M. J. Rahman, N. A. M. F. Ahmed, M. M. Abedin, B. Ahammed, M. Ali, M. J. Rahman, and M. Maniruzzaman, “Investigate the risk factors of stunting, wasting, and underweight among under-five Bangladeshi children and its prediction based on machine learning approach,” PLOS ONE, vol. 16, no. 6, Art. no. e0253172, 2021. https://doi.org/10.1371/journal.pone.0253172.

[35] AF. H. Bitew, C. S. Sparks, and S. H. Nyarko, “Machine learning algorithms for predicting undernutrition among under-five children in Ethiopia,” Public Health Nutrition, vol. 25, no. 2, pp. 269–280, 2022. https://doi.org/10.1017/S1368980021004262.

[36] O. N. Chilyabanyama, R. Chilengi, M. Simuyandi, C. C. Chisenga, M. Chirwa, K. Hamusonde, R. K. Saroj, N. T. Iqbal, I. Ngaruye, and S. Bosomprah, “Performance of machine learning classifiers in classifying stunting among under-five children in Zambia,” Children, vol. 9, no. 7, Art. no. 1082, 2022. https://doi.org/10.3390/children9071082.

[37] H. Shen, H. Zhao, and Y. Jiang, “Machine learning algorithms for predicting stunting among under-five children in Papua New Guinea,” Children, vol. 10, no. 10, Art. no. 1638, 2023. https://doi.org/10.3390/children10101638.

[38] E. Indrisari, H. Febiansyah, and B. Adiwinoto, “A systematic literature review on the application of machine learning for predicting stunting prevalence in Indonesia (2020–2024),” Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 14, no. 3, pp. 277–283, Jul. 2025. https://doi.org/10.32736/sisfokom.v14i3.2366.

[39] E. Ramadanti, D. A. Dinathi, C. S. K. Aditya, and D. R. Chandranegara, “Diabetes Disease Detection Classification Using Light Gradient Boosting (LightGBM) With Hyperparameter Tuning,” Sinkron: Jurnal dan Penelitian Teknik Informatika, vol. 8, no. 2, 2024. https://doi.org/10.33395/sinkron.v8i2.13530.