Analysis K-Nearest Neighbor Algorithm for Improving Prediction Student Graduation Time
Open Access
- 11 March 2020
- journal article
- Published by Politeknik Ganesha in sinkron
- Vol. 4 (2), 42-46
- https://doi.org/10.33395/sinkron.v4i2.10480
Abstract
Higher education plays a major role in improving the quality of education in Indonesia. The BAN-PT institution established by the government has a standard of higher education accreditation and study program accreditation. With the 4.0-based accreditation instrument, it encourages university leaders to improve the quality and quality of their education. One indicator that determines the accreditation of study programs is the timely graduation of students. This study uses the K-Nearest Neighbor algorithm to predict student graduation times. Students' GPA at the time of the seventh semester will be used as training data, and data of students who graduate are used as sample data. K-Nearest Neighbor works in accordance with the given sample data. The results of prediction testing on 60 data for students of 2015-2016, obtained the highest level of accuracy of 98.5% can be achieved when k = 3. Prediction results depend on the pattern of data entered, the more samples and training data used, the calculation of the K-Nearest Neighbor algorithm is also more accurate.Keywords
This publication has 12 references indexed in Scilit:
- MCENN: A variant of extended nearest neighbor method for pattern recognitionPattern Recognition Letters, 2020
- Sublinear time approximation of the cost of a metric k-nearest neighbor graphPublished by Society for Industrial & Applied Mathematics (SIAM) ,2020
- Prediksi Kelulusan Tepat Waktu Menggunakan Metode C4.5 DAN K-NN (Studi Kasus : Mahasiswa Program Studi S1 Ilmu Farmasi, Fakultas Farmasi, Universitas Muhammadiyah Purwokerto)Techno (Jurnal Fakultas Teknik, Universitas Muhammadiyah Purwokerto), 2019
- Analysis of Frequent Itemsets Mining Algorithm Againts Models of Different DatasetsJournal of Physics: Conference Series, 2019
- Aplikasi Prediksi Kelulusan Mahasiswa Berbasis K-Nearest Neighbor (K-NN)JTIM : Jurnal Teknologi Informasi dan Multimedia, 2019
- Improved Handwritten Digit Recognition using Quantum K-Nearest Neighbor AlgorithmInternational Journal of Theoretical Physics, 2019
- Penerapan Algoritma K-Nearest Neighbor Untuk Penentuan Peminatan Studi (Studi Kasus : Program Studi Teknik Informatika STMIK Amik Riau)Fountain of Informatics Journal, 2019
- Smart Intelligent Computing and ApplicationsPublished by Springer Science and Business Media LLC ,2019
- A generalized mean distance-based k-nearest neighbor classifierExpert Systems with Applications, 2018
- Implementasi Algoritma Apriori Pada Data Benchmark Kosarak Dan MushroomsJournal of Informatics and Telecommunication Engineering, 2017