Open AccessPrediction of Vocational Students Behaviour using The k-Nearest Neighbor Algorithm
Author(s) -
Fadliansyah Nasution,
Elviawaty Muiza Zamzami
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1566/1/012046
Subject(s) - vocational education , attendance , payment , k nearest neighbors algorithm , sample (material) , computer science , value (mathematics) , data mining , mathematics education , algorithm , psychology , artificial intelligence , machine learning , pedagogy , world wide web , chemistry , chromatography , economics , economic growth
This article discusses the implementation of the k-NN algorithm in predicting student behavior. The school is a management unit that has data that correlate with students. All student data is stored in an academic information system that can be processed to predict student behavior. One of the data assessing student behavior is in the database of counseling guidance. Some data that will be processed include attendance, lateness notes of problems, teacher responses, tuition payments, broken home. The sample being tested was the data of 100 vocational students from various classes and various majors and divided into two categories. From this experiment, it can be seen that the most accurate K value is the value of K = 1, 3 and 4. The accuracy of the testing data generated is 94.9%.