Prediksi Kesiapan Kerja Mahasiswa menggunakan Algoritme K-Means dan C4.5

Abstract

Student work readiness is quite influential on the existence of a university. The waiting time required by students to get a job can affect the mentality of students and the value of higher education from the assumptions of society. This will greatly affect the interest of parents or prospective students to continue their education at universities that have a bad image. Therefore, predictions of student work readiness before graduation are needed for consideration by higher education institutions to overcome the problem of waiting time for student work after graduation. The source of this research data is obtained from the Surakarta University database by utilizing alumni data from tracer studies as train data and 6-semester active student data as test data. The initial step taken is preprocessing to eliminate noise that can interfere with or affect the final result. The research method that will be used is to implement the K-Means and C4.5 algorithms for grouping and prediction processes. The data train used is 150 data and the testing data is 59 data. The results obtained by the K-Means algorithm can cluster 143 data correctly by comparing with the original data. The best cluster value obtained is K = 3.