Prediction of Students Study Period using K-Nearest Neighbor Algorithm

Abstract

Currently, many higher educations are highly oriented to improve the quality of education and students’ learning achievement. Student achievement determined based on the final grades on certain courses. This study is conducted to use a classification algorithm that applied to predict student study period based on student achievement of final grade. This study proposed K-Nearest Neighbor (K-NN) algorithm that classifies by estimate the distance of student grade. This study analyzes 1,989 computer science student grades data in BINUS University from 2016 to 2019 and the algorithm reaches accuracy of 93.2% in predicting study on-time status, 91.5% in predicting study total year and 75.63% in predicting study total semester. In addition, the accuracy was evaluated from 398 testing data. The conclusion of this study is K-NN Algorithm can be applied to predict student study period based on student grades and increase the graduation rates of students.