Prediction of Stunting Prevalence in Indonesia Using Ordinary Least Square (OLS)
DOI:
https://doi.org/10.33379/gtech.v8i3.4623Keywords:
Stunting, Prediction, Prevalence, Machine Learning, OLSAbstract
Stunting is a growth issue in children, a serious concern both in Indonesia and globally, affecting over 149 million children worldwide, including 6.3 million in Indonesia. Despite some reduction, achieving the national target by 2024 remains challenging. The government has issued a Presidential Regulation to address stunting, focusing on family nutrition and environmental hygiene. This study aims to predict stunting prevalence, develop a more accurate prediction model, provide a basis for policy, and contribute to the scientific literature on stunting in Indonesia. The methods used include comparing algorithms such as Neural Network (NN), RBF Network, SVR kernel RBF, and Ordinary Least Square (OLS). The evaluation shows significant performance variation: NN performs fairly well, RBF Network performs better, SVR kernel RBF also performs well, but OLS stands out with very accurate predictions, minimal error values, and high correlation.
References
Badan Pusat Statistik. (2019). Statistik Kesejahteraan Rakyat 2019. Jakarta, Indonesia: Badan Pusat Statistik. ISSN: 0215-4641. Katalog BPS: 4101002. No. Publikasi: 04210.1913
Badan Pusat Statistik. (2020). Statistik Kesejahteraan Rakyat 2020. Jakarta, Indonesia: Badan Pusat Statistik. ISSN: 0215-4641. Katalog BPS: 4101002. No. Publikasi: 04210.1913
Badan Pusat Statistik. (2021). Statistik Kesejahteraan Rakyat 2021. Jakarta, Indonesia: Badan Pusat Statistik. ISSN: 0215-4641. Katalog BPS: 4101002. No. Publikasi: 04210.2116
Badan Pusat Statistik. (2022). Statistik Kesejahteraan Rakyat 2022. Jakarta, Indonesia: Badan Pusat Statistik. ISSN: 0215-4641. Katalog BPS: 4101002. No. Publikasi: 04210.2216
Badan Pusat Statistik. (2023). Laporan Indeks Khusus Penanganan Stunting Kabupaten/Kota 2020-2021, Nomor Katalog: 4207003, Nomor Publikasi: 04200.2306
Badan Pusat Statistik. (2023). Statistik Kesejahteraan Rakyat 2023. Jakarta, Indonesia: Badan Pusat Statistik. ISSN: 0215-4641. Katalog BPS: 4101002. No. Publikasi: 04210.2316
Bitew, F., & others. (2021). Machine learning algorithms for predicting undernutrition among under-five children in Ethiopia. Public Health Nutrition.
Cholid, F., Trishnanti, D., & Azies, H. Al. (2019). Pemetaan Faktor-Faktor yang Mempengaruhi Stunting pada Balita dengan Geographically Weighted Regression (GWR) Mapping of The Factors Affecting Stunting on Toddlers with Geographically Weighted Regression (GWR). Dalam SEMNAkes 2019 “Improving the Quality of Health Tharough Advances in Research of Health Sciences,” (hal. 156–165). https://doi.org/10.17605/OSF.IO/9MZU7
Damodar Gujarati, (2019). Basic Econometrics, 4th Edition. Singapore: McGrawth Hill.
Darnila, E., & others. (2022). Supervised models to predict the Stunting in East Aceh. International Journal of Engineering, Science and Information Technology.
Das, S., Bafour, B., & Richardson, A. (2022). Prevalence of child undernutrition measures and their spatio-demographic inequalities in Bangladesh: an application of multilevel Bayesian modelling. BMC Public Health, 22(1008). https://doi.org/10.1186/s12889-022-13170-4.
Galasso, E., & Wagstaff, A. (2019). The Aggregate Income Losses from Childhood Stunting and The Returns to A Nutrition Intervention Aimed at Reducing Stunting. Economics and Human Biology, 34(August), 225–238. https://doi.org/10.1016/j.ehb.2019.01.010
Ginantra, N. L. W. S. R., et al. (2021). Data Mining dan Penerapan Algoritma. Medan: Yayasan Kita Menulis.
Haris, M. S., Anshori, M., & Khudori, A. N. (2023). Prediction of stunting prevalence in East Java Province with Random Forest algorithm. Jurnal Teknik Informatika (JUTIF), volume, nomor halaman. DOI: 10.20884/1.jutif.2023.4.1.614.
Haris, M. S., Khudori, A. N., & Kusuma, W. T. (2022). Perbandingan Metode Supervised Machine Learning untuk Prediksi Prevalensi Stunting di Provinsi Jawa Timur. Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), volume, nomor halaman. doi: 10.25126/jtiik.202296744.
Indarwati, T., Irawati, T., & Rimawati, E. (2019). Penggunaan Metode Linear Regression untuk Prediksi Penjualan Smartphone. Jurnal Teknologi Informasi Dan Komunikasi (TIKomSiN), https://doi.org/10.30646/tikomsin.v6i2.369.
Kementerian Kesehatan. (2021). Buku Saku Hasil Studi Status Gizi Indonesia (SSGI) Tingkat Nasional, Provinsi, dan Kabupaten/Kota Tahun 2021. Jakarta, Indonesia.
Kementerian Kesehatan. (2021). Prediksi Angka Stunting Tahun 2020. Jakarta, Indonesia.
Kementerian Kesehatan. (2021). Studi Status Gizi Balita Indonesia (SSGBI) Tahun 2019 dan Studi Determinan Status Gizi (SDSG) Pada Masa Pendemi Covid-19 Tahun 2020. Jakarta, Indonesia.
Kementerian Kesehatan. (2023). Hasil Survei Status Gizi Indonesia (SSGI) 2022. Jakarta, Indonesia.
Mambang, F. D., Marleny, & Zulfadhilah, M. (2023). Prediction of linear model on stunting prevalence with machine learning approach. Bulletin of Electrical Engineering and Informatics, volume, nomor halaman. DOI: 10.11591/eei.v12i1.4028.
Paudpedia. (2023). 149 Juta Anak di Dunia Alami Stunting Sebanyak 6,3 Juta di Indonesia, Wapres Minta Keluarga Prioritaskan Kebutuhan Gizi.
Rokom. (2023). Prevalensi Stunting di Indonesia Turun ke 21,6% dari 24,4%.
UNICEF Indonesia. Ringkasan Kajian Gizi Ibu dan Anak. Diakses dari www.unicef.org pada bulan April 2024.
World Health Organization (WHO). Diakses dari www.who.int pada bulan April 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Benny Putra, Alva Hendi Muhammad
This work is licensed under a Creative Commons Attribution 4.0 International License.
