Open AccessEducational Data Mining Analysis Using Classification Techniques
Author(s) -
Agung Triayudi,
Wahyu Oktri Widyarto
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1933/1/012061
Subject(s) - educational data mining , computer science , random forest , data mining , support vector machine , data science , student achievement , multilayer perceptron , theme (computing) , machine learning , field (mathematics) , artificial intelligence , mathematics education , artificial neural network , academic achievement , world wide web , mathematics , pure mathematics
Currently, data mining is being needed in various fields to obtain analysis results from certain aspects that are needed. One of the fields that make use of data mining is education. The education sector uses data mining to determine the level of performance or achievement of its students. With data mining, the education sector can also evaluate student achievement and take the next step in increasing that achievement. Data mining in education is also known as Educational Data Mining (EDM). In this study, the theme discussed was the prediction of student learning habits and steps that could be taken to improve student achievement at the university. In this study, three (3) classification algorithms were used, namely Multilayer Perceptron, Random Forest, and Support Vector Machine. This is done to find the best results from each algorithm.