OPTIMIZATION OF C.45 ALGORITHM WITH SPLITTING METHOD FOR TODDLER NUTRITION CLASSIFICATION

I Made Ari Prayoga; Ketut Queena  Fredlina; Nengah Widya Utami

Authors

I Made Ari Prayoga Informatic Engineering, Primakara University
Ketut Queena Fredlina Informatic Engineering, Primakara University
Nengah Widya Utami Informatic Engineering, Primakara University

Keywords:

Nutritional status of toddlers, data mining, classification, C4.5 algorithm

Abstract

Toddler nutritional health is a critical aspect of community development, yet Indonesia continues to face significant challenges in this domain. Posyandu Manukaya Village, a village-level community health service unit, struggles with identifying toddler nutritional status due to manual record-keeping. This study addresses the issue by applying the C4.5 algorithm to classify toddler nutritional status using data from the Tampaksiring I Health Center, comprising a clean dataset of 970 entries. The research adopts the CRISP-DM (Cross Industry Standard Process for Data Mining) framework, with tailored stages including data preparation, model training, and evaluation using confusion matrix. The study identified weight (BB) as the most influential attribute for classification. Among the three attribute separation methods tested, Gain Ratio achieved the best accuracy of 89%, followed by Information Gain at 88%, and Gini Index at 86%. The resulting model was integrated into a simple website using Flask and Joblib, enabling early detection of toddler nutritional status. This research demonstrates the potential of integrating machine learning into public health initiatives and provides a strong foundation for enhancing toddler health monitoring at Posyandu Manukaya Village. Future research should use larger, balanced datasets and more attributes to enhance the model and support early toddler health interventions.

References

Data Science Process Allieance. (2021). Evaluating CRISP-DM For Data Science. https://www.datascience-pm.com/crisp-dm-2/

Ginting, K., Rinawati, R., Minaria, M., & Laily, I. I. (2022). Korelasi Kondisi Awal Ibu Dengan Karakter Gizi Anak Balita. Jurnal Ilmiah Kesehatan Keperawatan, 18(1), 18–28. https://doi.org/10.26753/jikk.v18i1.533

Hafizan, H., & Putri, A. N. (2020). Penerapan Metode Klasifikasi Decision Tree Pada Status Gizi Balita Di Kabupaten Simalungun. In KESATRIA: Jurnal Penerapan Sistem Informasi (Komputer & Manajemen) (Vol. 1, Issue 2). https://doi.org/10.30645/kesatria.v1i2.23

Islam, H. I., Mulyadien, M. K., & Enri, U. (2022). Penerapan Algoritma C4. 5 dalam Klasifikasi Status Gizi Balita. Jurnal Ilmiah Wahana Pendidikan, 8(10), 116–125. https://doi.org/10.5281/zenodo.6791722

Kementerian Kesehatan RI. (2016). Hasil Pemantauan Status Gizi (PSG). In Kementerian Kesehatan RI.

Mahpuz, M., Muliawan Nur, A., & Samsu, L. M. (2022). Penerapan Algoritma C4.5 Dalam Mengklasifikasi Status Gizi Balita Pada Posyandu Desa Dames Damai Kabupaten Lombok Timur. Infotek : Jurnal Informatika Dan Teknologi, 5(1), 72–81. https://doi.org/10.29408/jit.v5i1.4414

Marini, Tambunan, H. S., Siregar, Z. A., Windarto, A. P., & Rizki, F. (2022). Penerapan Data Mining Klasifikasi Gizi Bayi Dengan Algoritma Decision Tree C4.5. In ZAHRA Buletin Big Data (Vol. 1, Issue 2). https://ejurnal.pdsi.or.id/index.php/zahra/index

Markoulidakis, I., Rallis, I., Georgoulas, I., Kopsiaftis, G., Doulamis, A., & Doulamis, N. (2021). Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem. Technologies, 9(4). https://doi.org/10.3390/technologies9040081

Marniati. (2021). Manajemen Pemanfaatan Posyandu Balita.

Matthew, Dr. N. (2012). Data mining for the masses.

Mujiyono, S., & Syaiful, N. (2023). Prediction of Nutritional Status of Toddlers Using C4. 5 Algorithm. In Jurnal Mandiri IT (Vol. 12, Issue 1). http://ejournal.isha.or.id/index.php/Mandiri/article/view/229%0Ahttp://ejournal.isha.or.id/index.php/Mandiri/article/download/229/298

Muslim, M. A., Prasetiyo, B., Mawarni, E. L. H., Herowati, A. J., Mirqotussa’adah, Rukmana, S. H., & Nurzahputra, A. (2019). Buku Data Mining.

Rajoub, B. (2020). Supervised and unsupervised learning. In Biomedical Signal Processing and Artificial Intelligence in Healthcare (pp. 51–89). Elsevier. https://doi.org/10.1016/B978-0-12-818946-7.00003-2

Republik Indonesia. (2009). UNDANG-UNDANG REPUBLIK INDONESIA NOMOR 36 TAHUN 2009 TENTANG KESEHATAN.

Schröer, C., Kruse, F., & Gómez, J. M. (2021). A systematic literature review on applying CRISP-DM process model. Procedia Computer Science, 181(2019), 526–534. https://doi.org/10.1016/j.procs.2021.01.199

Witten, I. H., Frank, E., & Hall, M. A. (2011). Data Mining (Third Edition). In Data Mining (Third Edition). http://www.sciencedirect.com/science/article/pii/B9780123814791000162