Implementation of artificial neural network and support vector machine algorithm on student graduation prediction model on time

Yennimar Yennimar (Universitas Prima Indonesia, Indonesia)
M. Rafi Faturrahman (Universitas Prima Indonesia, Indonesia)
Siwa Nesen (Universitas Prima Indonesia, Indonesia)
M. Anhar Guci (Universitas Prima Indonesia, Indonesia)
Samuel Rifaldi Pasaribu (Universitas Prima Indonesia, Indonesia)

Jurnal Mantik
Vol. 7 No. 2 (2023): Agustus: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)

This research aims to evaluate how Artificial Neural Network (ANN) and Support Vector Machine (SVM)  algorithms can be used to predict student graduation on time. This research uses student data from Universitas Prima Indonesia (UNPRI) Medan to build a prediction model. ANN and SVM methods have been applied and compared to see the performance of each model. The test results show that the SVM model is superior in terms of accuracy and computational speed compared to the ANN model. In addition, the test results also show that the SVM model can be used to predict student graduation on time with an accuracy of 96.34%. This result shows that the SVM model is more effective in predicting student graduation on time compared to the ANN model