APPLICATION OF K-NEAREST NEIGHBOR ALGORITHM IN RECOMMENDING STUDENTS' SPECIALIZATIONS (CASE STUDY: CIVIL ENGINEERING PROGRAM AT KHAIRUN UNIVERSITY)
DOI:
https://doi.org/10.33387/jati.v3i1.222Keywords:
Student Specialization, Recommendation System, KNN, K-Nearest NeighborAbstract
The specialization of students in a particular field of study significantly impacts their academic journey and the selection of their final projects. A deep understanding and recognition of these specializations are crucial factors in determining the academic success and graduation of students, particularly within the context of their chosen areas of focus. The objective of this research is to apply the k-nearest neighbor algorithm in recommending student specializations in the Civil Engineering Program at Khairun University. This study assists students by providing recommendations for specializations based on individual criteria and academic performance. Testing is conducted by comparing the verified specialization outcomes of students with the results generated by the system. The findings of this research produce a recommendation system for student specializations in the Civil Engineering Program at Khairun University, using the k-nearest neighbor algorithm. Testing with a sample of 20 students who already have specializations reveals that accuracy varies depending on the value of K used. For K=3, an accuracy rate of 50% is obtained, while for K=7, an accuracy rate of 55% is observed, and for K=10, an accuracy rate of 40% is achieved. The lower accuracy is primarily attributed to data imbalance rather than errors in the algorithm.
References
L. Anshori, R. Regasari, and M. Putri, “Implementasi Metode K-Nearest Neighbor untuk Rekomendasi Keminatan Studi ( Studi Kasus : Jurusan Teknik Informatika Universitas Brawijaya ),” vol. 2, no. 7, 2018.
N. Tri Romadloni, I. Santoso, and S. Budilaksono, “Perbandingan Metode Naive Bayes, KNN, dan Decision Tree Terhadap Analisis Sentimen Transportasi KRL Commuter Line,” J. IKRA-ITH Inform., vol. 3, no. 2, pp. 1–9, 2019.
A. Sumiah and N. Mirantika, “Perbandingan Metode K-Nearest Neighbor dan Naive Bayes untuk Rekomendasi Penentuan Mahasiswa Penerima Beasiswa pada Universitas Kuningan,” Buffer Inform., vol. 6, no. 1, pp. 1–10, 2020.
Yuli Mardi, “Data Mining : Klasifikasi Menggunakan Algoritma C4 . 5 Data mining merupakan bagian dari tahapan proses Knowledge Discovery in Database ( KDD ) . Jurnal Edik Informatika,” J. Edik Inform., vol. 2, no. 2, pp. 213–219, 2019.
F. Shidiq, “Penerapan Metode K-Nearest Neighbor (KNN) Untuk Menentukan Ikan Cupang Dengan Ekstraksi Fitur Ciri Bentuk Dan Canny,” Innov. Res. Informatics, vol. 3, no. 2, pp. 39–46, 2021, doi: 10.37058/innovatics.v3i2.3093.
U. Erdiansyah, A. Irmansyah Lubis, and K. Erwansyah, “Komparasi Metode K-Nearest Neighbor dan Random Forest Dalam Prediksi Akurasi Klasifikasi Pengobatan Penyakit Kutil,” J. Media Inform. Budidarma, vol. 6, no. 1, p. 208, 2022, doi: 10.30865/mib.v6i1.3373.
A. A. Wahid, “Analisis Metode Waterfall Untuk Pengembangan Sistem Informasi,” J. Ilmu-ilmu Inform. dan Manaj. STMIK, no. November, pp. 1–5, 2020.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Jurnal Jaringan dan Teknologi Informasi
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
