M. Nadhif Pradiza Husni
Universitas Pembangunan Panca Budi

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Penerapan Algoritma K-Nearest Neighbor (KNN) untuk Prediksi Kelayakan Beasiswa pada Sistem Informasi Siswa Sekolah Sinar Husni Medan Berbasis Web M. Nadhif Pradiza Husni; Hafni; Muhammad Zen
Jurnal Nasional Teknologi Komputer Vol 6 No 4 (2026): Oktober 2026
Publisher : CV. Hawari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61306/jnastek.v6i4.544

Abstract

Education is a fundamental right, yet family economic limitations often hinder educational equality. The scholarship program at Sinar Husni Medan School was established to address this issue, but the conventional (manual) selection process is identified as time-consuming and vulnerable to examiner subjectivity bias. This research aims to design and implement the K-Nearest Neighbor (KNN) algorithm integrated into a web-based Information System to automate the prediction of scholarship eligibility objectively. The computational parameters evaluated include Parents' Income, Number of Dependents, Average Report Card Grades, and Distance of Residence. Given the high variation in data scales, this study applied Min-Max Scaler normalization preprocessing before calculating matrix proximity using Euclidean Distance. Based on algorithm testing using a neighborhood parameter of k=5 against the student dataset, the developed machine learning model successfully achieved an accuracy rate of 90.00%, precision of 91.67%, and recall of 88.00%. The conclusion of this research proves that the KNN algorithm is highly capable of solving educational eligibility multi-criteria. The implementation of this information system significantly improves operational time efficiency and decision data integrity standardization within the Sinar Husni Medan School environment.