<![CDATA[The problem addressed was the limited use of dropout prediction models, which had generally focused on algorithm performance and had not been integrated into an academic monitoring system design.This study aimed to develop a web-based prototype information system for predicting student dropout risk using the CatBoost algorithm to support academic monitoring. The development method used was Prototyping, while the prediction model was built from the Predict Students Dropout and Academic Success dataset, which was reduced to 3,399 records with two classes, namely dropout and graduate. The results showed that the developed prototype included manual prediction, CSV import, prediction monitoring, and role-based reporting features. The CatBoost model achieved 90.29% accuracy, 85.33% precision, 88.76% recall, and 87.01% F1-score. These findings indicated that the prototype had the potential to serve as a basis for developing an early detection system for students at risk of dropout. Keywords: Academic monitoring; CatBoost; Dropout prediction; System prototype; Web-based information system AbstrakPermasalahan yang diangkat adalah keterbatasan pemanfaatan model prediksi dropout yang umumnya masih berfokus pada performa algoritme dan belum terintegrasi ke dalam rancangan sistem pemantauan akademik. Penelitian ini bertujuan mengembangkan prototype sistem informasi prediksi risiko dropout mahasiswa berbasis web menggunakan algoritme CatBoost untuk mendukung pemantauan akademik. Metode pengembangan yang digunakan adalah Prototyping, sedangkan model prediksi dibangun dari dataset Predict Students Dropout and Academic Success yang diseleksi menjadi 3.399 data dengan dua kelas, yaitu dropout dan graduate. Hasil penelitian menunjukkan bahwa prototype yang dikembangkan memuat fitur prediksi manual, impor file CSV, monitoring hasil prediksi, dan laporan berbasis peran pengguna. Model CatBoost memperoleh accuracy 90,29%, precision 85,33%, recall 88,76%, dan F1-score 87,01%. Temuan ini menunjukkan bahwa prototype tersebut berpotensi menjadi dasar pengembangan sistem deteksi dini mahasiswa berisiko dropout. Kata kunci: Pemantauan akademik]]>
