Various scenarios to improve the education system have been carried out. One of them is the application of educational data mining to gain the student’s academic achievement, also decreasing the risk of drop out. The data was collected from three private universities in Jakarta, where it consists of academic, social, and economic information, as the demographics of 350 students with 23 attributes. Educational Data Mining applied a WEKA’s tool that takes a rule in this study, while the classification phases applied PART, BayesNet, Random Tree, and J48 as their methods of classification. Attributes that have a significant influence on the classification process are selected as a medium of classification. The end of this study explained that Random Tree plays a significant part in classifying all possibilities related to predicting students’ academic performance. The accuracy level is relatively high, and the misclassification rate is also low. Besides, the Apriori algorithm also plays a significant role in finding association rules of educational data mining of all the best attributes and rules available.
CITATION STYLE
Triayudi, A., Widyarto, W. O., & Rosalina, V. (2022). Analysis of Educational Data Mining Using WEKA for the Performance Students Achievements. In Lecture Notes in Electrical Engineering (Vol. 898, pp. 1–10). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-1804-9_1
Mendeley helps you to discover research relevant for your work.