Volume 20 No 12 (2022)
 Download PDF
Naive Bayes Classifier Method Analysis and Support Vector Machine (SVM) Student Graduation Prediction
Siti Mukodimah, Muhamad Muslihudin , Dwi Rohmadi Mustofa , Didi Susianto , Suyono
Abstract
Graduating on time is the dream of every student, but the reality is not as expected. Many students graduate after more than four years. Based on data, the Lampung region has a total of 84 institutions with 24,216 new students per year and 19,486 graduates per year. The number of college graduates only reached 54.96 % of the number of new students enrolled each year in universities. This means that the number of students entering and leaving the university has not been balanced every year so that there is an accumulation of students in each graduation period. With this research can identify the causes of delays in graduation students. Prediction of student graduation based on predetermined parameters can help classify student data, thus helping students who are indicated to be not on time to complete their studies. In this study, two models were used to predict student graduation, namely the Naïve Bayes Classifier and SVM. Both methods are classification methods. The Naïve Bayes method is an algorithm that is simple, fast and has a high level of accuracy, while the SVM method is a method that is able to identify separate Hyperplanes that maximize the margin between two different classes. Based on observations and research studies that have been carried out at STMIK Pringsewu have not led to the identification of the causes of student delays in completing studies, so it is necessary to predict student graduation using the right classification method to describe the class on time of graduation. The results of this study are taken into consideration by the leadership in making internal higher education policies in an effort to balance the ratio of student enrollment and student graduation at STMIK Pringsewu
Keywords
Prediction, Punctuality, Graduation, Classification Method
Copyright
Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.