Aplikasi Prediksi Kelulusan Mahasiswa Berbasis K-Nearest Neighbor (K-NN)

  • Lalu Abd Rahman Hakim Universitas Bumigora
  • Ahmad Ashril Rizal Universitas Bumigora
  • Dwi Ratnasari Universitas Bumigora
Keywords: Student, K-Nearest Neighbor, Student Graduation, Data Mining

Abstract

Students are important assets for an educational institution and for this reason, it is necessary to pay attention to the student's graduation rate on time. Presentation of the ups and downs of students' ability to complete their studies on time is one of the elements of campus accreditation assessment. Based on data from the Study Program Section in the last 3 years the student graduation presentation is only 25% of the total students who can complete their studies on time. In this study using the K-Nearest Neighbor algorithm which aims to be able to identify student graduation in new cases by adapting solutions from previous cases that have closeness to new cases. This algorithm has the role to get the value of the closeness of the new case to the old case, which in turn the most population in area K with the closest value obtained by the student is predicted whether to pass on time or not on time. This study uses Roger S. Pressman's waterfalll method, namely Communication, Planning, Modeling, and Construction. Based on the tests carried out using K-Fold Cross Validation, the highest accuracy in the third model was 80% when folded 4th and 61% when the K value = 1. While testing using the Confusion Matrix obtained the highest accuracy of 98% at K = 1 for classification "Timely", and 98% at K = 2 for classification "Not Timely"

Downloads

Download data is not yet available.

References

[1] Buku Pedoman Akademik STMIK Bumigora Mataram, 2013
[2] Azwar.(2004). Penyusunan Skala Psikologi. Yogyakarta: Pustaka Pelajar
[3] Buku VI Matriks Penilaian Instrumen Akreditasi Program Studi Badan Akreditasi Nasional Perguruan Tinggi, 2008
[4] Rohman, Abdul. ”Model Algoritma K-Nearest Neighbor (KNN) Untuk Prediksi Kelulusan Mahasiswa.”Jurnal Unpand 1.1 (2015).Web
[5] Kamber, H. &. (2006). Data Mining Concept and Tehniques. San Fransisco: Morgan Kauffman
[6] Gorunescu, F., 2011, Data Mining: Concepts, Models and Techniques, Springer, Berlin Heidelberg
Published
2019-05-10
How to Cite
Hakim, L. A. R., Rizal, A. A., & Ratnasari, D. (2019). Aplikasi Prediksi Kelulusan Mahasiswa Berbasis K-Nearest Neighbor (K-NN). JTIM : Jurnal Teknologi Informasi Dan Multimedia, 1(1), 30-36. https://doi.org/10.35746/jtim.v1i1.11
Section
Articles