Prediction of Graduation of Students of the Lampung School of Technology Nusantara using the K-Nearest Neighbor and Naive Bayes Algorithm

Febri Suganda, Handoyo Widi Nugroho, Idris Asmuni


Predicting student graduation is the main factor for campuses to be able to assess the performance of each study program in learning achievement in each semester. Nusantara High School of Technology (STTN) Lampung has difficulty predicting graduation, so the machine learning approach with the K-Nearest Neighbor algorithm and the Naïve Bayes algorithm is very important in predicting graduation. In this
paper, we discuss the K-Nearest Neighbor and Naïve Bayes methods which in research at STTN Lampung used the Rapidminer 9.1 application, with a total data of 372 student graduations which were then processed by previous data to obtain samples to be studied, then obtained a sample of 186 graduation students from the 2017 class. and 2019, for S1 Industrial Engineering and S1 Electrical. The results showed that the approach with the Naïve Bayes algorithm had a higher prediction accuracy of 89.09% compared to the K-Nearest Neighbor algorithm which obtained an accuracy rate of 74.77%. Further research can be carried out with other methods and samples from other year classes to produce more diverse predictions.

Keywords — Prediction of student graduation, K-Nearest Neighbor Algorith,Naive Bayes Algorithm

Full Text:



  • There are currently no refbacks.

Proceeding International Conference on Information Technology and Business (ICITB) is abstracting and indexing in the following databases:


Managing By: Lembaga Penelitian dan Pengabdian kepada Masyarakat (LPPM)

Publisher: Institut Informatika dan Bisnis Darmajaya
Address: Jl. Z.A. Pagar Alam No. 93 Gedong Meneng, Bandar Lampung Lampung



Creative Commons License

IC-BITERA is licensed under a Creative Commons Attribution 4.0 International License.