Analisis Pengaruh Fitur Terhadap Tinggi Badan Anak menggunakan SHAP
DOI:
https://doi.org/10.26418/jp.v11i2.96734Keywords:
prediksi tinggi badan, SHAP, fitur, anak, machine learningAbstract
Tinggi badan anak merupakan indikator penting dalam menilai status pertumbuhan dan gizi. Meskipun hubungan antara faktor antropometri dan tinggi badan telah banyak diteliti, pemahaman kuantitatif mengenai kontribusi relatif fitur dalam model prediktif masih perlu dieksplorasi. Penelitian ini bertujuan menganalisis pengaruh fitur terhadap tinggi badan anak menggunakan machine learning berbasis regresi dan interpretasi model SHAP. Analisis dilakukan dengan kerangka CRISP-DM yang mencakup siklus analitik data. Dataset penelitian terdiri dari 100.000 entri anak dengan lima fitur utama: umur, berat badan, stunting, wasting, dan jenis kelamin. Pemodelan dilakukan secara otomatis menggunakan PyCaret dan dievaluasi dalam tiga skenario jumlah fitur: lima, tiga, dan satu, untuk menilai dampaknya terhadap akurasi dan kontribusi fitur. Hasil menunjukkan bahwa fitur umur secara konsisten memiliki pengaruh terbesar dalam semua skenario. Model lima fitur menghasilkan akurasi tertinggi (R ² = 0,9276), sementara model tiga fitur tetap kompetitif (R ² = 0,9233). Temuan ini menunjukkan bahwa fitur antropometri dasar cukup informatif untuk prediksi tinggi badan secara efisien dan interpretatif.References
R. A. Rahmadani, R. Wahyuni, D. Arda, A. S. Musrah, and R. Sabriana, “Socioeconomic Factors with Nutritional Status of Toddlers,†Jurnal Ilmiah Kesehatan Sandi Husada, vol. 12, no. 2, pp. 445–451, Dec. 2023, doi: 10.35816/jiskh.v12i2.1115.
J. Ipmawati and I. Unggara, “Analisis Status Gizi Anak Menggunakan Metode Klastering pada Dataset Anthropometri,†bit-Tech, vol. 7, no. 2, pp. 494–504, Dec. 2024, doi: 10.32877/bt.v7i2.1869.
O. Martony, “Stunting di Indonesia: Tantangan dan Solusi di Era Modern,†Journal of Telenursing (JOTING), vol. 5, no. 2, pp. 1734–1745, Aug. 2023, doi: 10.31539/joting.v5i2.6930.
A. Rimpler, H. A. L. Kiers, and D. van Ravenzwaaij, “To interact or not to interact: The pros and cons of including interactions in linear regression models,†Behav Res Methods, vol. 57, no. 3, Mar. 2025, doi: 10.3758/s13428-025-02613-6.
A. Shrestha and A. Mahmood, “Review of deep learning algorithms and architectures,†2019, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2019.2912200.
S. Muliani, B. Sukma Negara, M. Irsyad, I. Iskandar, and J. Teknik Informatika, “Application of SHapley Additive exPlanations (SHAP) in Deep Learning for Lung Disease Detection Using X-ray Images,†Journal of Artificial Intelligence and Software Engineering, vol. 5, no. 2, pp. 709–719, 2025, doi: 10.30811/jaise.v5i2.7044.
X. Qi, S. Wang, C. Fang, J. Jia, L. Lin, and T. Yuan, “Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants,†Redox Biol, vol. 79, Feb. 2025, doi: 10.1016/j.redox.2024.103470.
Z. Song et al., “Integrating SHAP analysis with machine learning to predict postpartum hemorrhage in vaginal births,†BMC Pregnancy Childbirth, vol. 25, no. 1, Dec. 2025, doi: 10.1186/s12884-025-07633-w.
V. Vimbi, N. Shaffi, and M. Mahmud, “Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer’s disease detection,†Dec. 01, 2024, Springer Science and Business Media Deutschland GmbH. doi: 10.1186/s40708-024-00222-1.
M. M. Islam, T. Nasrin, B. A. Walther, C. C. Wu, H. C. Yang, and Y. C. Li, “Prediction of sepsis patients using machine learning approach: A meta-analysis,†Comput Methods Programs Biomed, vol. 170, pp. 1–9, Mar. 2019, doi: 10.1016/j.cmpb.2018.12.027.
H. A. Santoso, N. S. Dewi, S. C. Haw, A. D. Pambudi, and S. A. Wulandari, “Enhancing nutritional status prediction through attention-based deep learning and explainable AI,†Intell Based Med, vol. 11, Jan. 2025, doi: 10.1016/j.ibmed.2025.100255.
UNICEF, WHO, and World Bank Group Joint Child Malnutrition Estimates, “LEVELS AND TRENDS IN CHILD MALNUTRITION 47 million 38 million,†2020.
A. Wicaksono, D. Prasetyo, Y. Mar’atullatifah, D. U. Iswavigra, H. Mahmudah, and A. Hapsari, “Data Analysis and Explainable Machine learning for Stunting Prediction,†2025.
D. B. Saputra, V. Atina, F. E. Nastiti, and F. I. Komputer, “PENERAPAN MODEL CRISP-DM PADA PREDIKSI NASABAH KREDIT MENGGUNAKAN ALGORITMA RANDOM FOREST,†2024. [Online]. Available: http://jom.fti.budiluhur.ac.id/index.php/IDEALIS/indexDwiBagusSaputra|http://jom.fti.budiluhur.ac.id/index.php/IDEALIS/index|
N. Novalina, I. A. A. Tarigan, F. K. Kameela, and M. Rizkinia, “Benchmarking machine learning algorithm for stunting risk prediction in Indonesia,†Bulletin of Electrical Engineering and Informatics, vol. 14, no. 3, pp. 2252–2263, Jun. 2025, doi: 10.11591/eei.v14i3.8997.
F. Martinez-Plumed et al., “CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,†IEEE Trans Knowl Data Eng, vol. 33, no. 8, pp. 3048–3061, Aug. 2021, doi: 10.1109/TKDE.2019.2962680.
A. M. Shimaoka, R. C. Ferreira, and A. Goldman, “The evolution of CRISP-DM for Data Science: Methods, Processes and Frameworks,†SBC Reviews on Computer Science, vol. 4, no. 1, pp. 28–43, Oct. 2024, doi: 10.5753/reviews.2024.3757.
U. Kannengiesser and J. S. Gero, “MODELLING THE DESIGN OF MODELS: AN EXAMPLE USING CRISP-DM,†in Proceedings of the Design Society, Cambridge University Press, 2023, pp. 2705–2714. doi: 10.1017/pds.2023.271.
O. Azeroual, R. Nacheva, A. Nikiforova, and U. Störl, “A CRISP-DM and Predictive Analytics Framework for Enhanced Decision-Making in Research Information Management Systems,†Informatica (Slovenia), vol. 49, no. 18, pp. 67–86, 2025, doi: 10.31449/inf.v49i18.5613.
A. Arif and D. Gusmaliza, “Sistem Cerdas Deteksi Status Gizi Anak melalui Eksplorasi Algoritma C.45 dan Forward Feature Selection,†Edumatic: Jurnal Pendidikan Informatika, vol. 8, no. 2, pp. 774–753, Dec. 2024, doi: 10.29408/edumatic.v8i2.28014.
