Open AccessThe uses of educational data mining in academic performance analysis at higher education institutions (case study at UNJANI)
Author(s) -
Yulison Herry Chrisnanto,
Gunawan Abdullah
Publication year - 2021
Publication title -
matrix : jurnal manajemen teknologi dan informatika/matrix: jurnal manajemen teknologi dan informatika
Language(s) - English
Resource type - Journals
eISSN - 2580-5630
pISSN - 2088-284X
DOI - 10.31940/matrix.v11i1.2330
Subject(s) - educational data mining , computer science , cluster analysis , higher education , medoid , association rule learning , data mining , data science , set (abstract data type) , data set , support vector machine , decision tree , machine learning , artificial intelligence , political science , law , programming language
Education is an important thing in a person's life, because by having adequate education, one's life will be better. Education can be obtained formally through formal institutions that constructively provide a person's abilities academically. This study aims to determine student performance in terms of academic and non-academic domains at a certain time during their education using techniques in data mining (DM) which are directed towards academic data analysis. Academic performance is delivered through the Educational Data Mining (EDM) integrated data mining model, in which the techniques used include classification (ID3, SVM), clustering (k-Means, k-Medoids), association rules (Apriori) and anomaly detection (DBSCAN). The data set used is academic data in the form of study results over a certain period of time. The results of EDM can be used for analysis related to academic performance which can be used for strategic decision making in aca-demic management at higher education institutions. The results of this study indicate that the use of several techniques in data mining together can maximize the ability to analyze academic performance with the same data source and produce different analysis patterns.