<![CDATA[Kesehatan bayi merupakan indikator penting kualitas generasi masa depan, namun deteksi dini risiko kesehatan sering terkendala keterbatasan tenaga medis dan sistem pemantauan efektif. Penelitian ini mengembangkan sistem prediksi risiko kesehatan bayi berusia 0-30 hari menggunakan algoritma Gradient Boosting berdasarkan parameter tumbuh kembang. Metode pengembangan sistem menggunakan Agile Scrum dengan dataset "Infant Wellness and Risk Evaluation" yang melalui tahap pra-pemrosesan data dan feature engineering. Hasil evaluasi menunjukkan model mencapai akurasi 94%, recall 84% untuk kelas berisiko, dan precision 71%. Analisis feature importance mengidentifikasi age_days, oxygen_saturation, dan heart_rate_zscore sebagai fitur paling berpengaruh. Sistem prediksi berbasis web yang dihasilkan ini nantinya diharapkan dapat menjadi alat bantu yang efektif bagi tenaga medis. Infant health is an important indicator of future generation quality, but early detection of health risks is often constrained by limitations of medical personnel and effective monitoring systems. This research develops a health risk prediction system for infants aged 0-30 days using Gradient Boosting algorithm based on growth and development parameters. The system development method uses Agile Scrum with "Infant Wellness and Risk Evaluation" dataset through data preprocessing and feature engineering stages. Evaluation results show the model achieves 94% accuracy, 84% recall for at-risk class, and 71% precision. Feature importance analysis identifies age_days, oxygen_saturation, and heart_rate_zscore as the most influential features. The resulting web-based system has potential as an effective assistance tool for medical personnel. ]]>
