Data Mining Untuk Memprediksi Nilai Kelulusan Siswa

PINAT, Viona Aderisti (2021) Data Mining Untuk Memprediksi Nilai Kelulusan Siswa. Undergraduate thesis, Universitas Katolik Widya Mandira Kupang.

	Text ABSTRAK.pdf Download (617kB)
	Text BAB I.pdf Download (149kB)
	Text BAB II.pdf Restricted to Repository staff only Download (615kB)
	Text BAB III.pdf Restricted to Repository staff only Download (317kB)
	Text BAB IV.pdf Restricted to Repository staff only Download (509kB)
	Text BAB V.pdf Restricted to Repository staff only Download (63kB)
	Text BAB VI.pdf Download (12kB)

Abstract

Data mining is a way to find new information taken from large amounts of data that helps in decision making. By utilizing student parent data, student graduation, and student average scores as data sources, it is hoped that it can produce information about the comparison of student graduation through data mining techniques. The graduation comparison category is measured from the average score of the report cards from grade 1 to grade 5 and the average UAS (Final School Examination) score. There are 2 types of data mining technique processes, namely, Data Trainning and Data Testing. The calculation technique is carried out using 5 methods, namely Naïve Bayes, decision tree, K-NN, Neural Network, and SVM. The Comparison results show that in the use of data mining classification algorithms used, namely naïve bayes, decision tree, K-NN, Neural Network, and SVM, it can be seen that the decision tree algorithm is the right and accurate algorithm used to predict student graduation with a value percentage of 868 %.

Actions (login required)

View Item