Analisis Prediksi Penerima Bantuan Bea Study Menggunakan Algoritma Id3, Naïve Bayes Dan K-Nearest Neighbor (Studi Kasus Pada Lembaga Amil Zakat Rydha)

Abstract

The RYDHA Amil Zakat Institution has not yet implemented a data-driven predictive system to objectively determine B-Best scholarship recipients, leaving the selection process manual and prone to bias. This study aims to compare the performance of ID3, Naïve Bayes, and K-Nearest Neighbors (KNN) algorithms in classifying scholarship eligibility. Primary data were obtained from the 2024 B-Best applicants’ records, including demographic, socio-economic, academic, and supporting documents, while secondary data consisted of selection guidelines and internal reports, collected through interviews, documentation, and observation. Data analysis employed the three algorithms with evaluation using the Confusion Matrix and ROC Curve. The results show that KNN achieved the best performance with 96.3% accuracy, 0.958 AUC, 0.944 F1-score, 0.944 precision, and 0.944 recall, thus recommended as the predictive model to support a more objective and accurate scholarship selection system.