Main Article Content
The STMIK Informatics Engineering Study Program Nurdin Hamzah Jambi uses Student's Values from Attendance, Tasks, UTS, and UAS values to classify student Academic performance. During this time the technique used to classify the academic performance of students using statistical algorithms but the algorithm does not provide any effective results. Therefore, a combination of Mining Data K-Means Clustering is used to provide more effective results. The purpose of this study is to develop the implementation of the K-Means algorithm to measure the academic performance of students each semester in the STMIK Informatics Engineering Study Program Nurdin Hamzah Jambi. The Data Mining method used is k-means clustering using the Rapidminer application. In this study, the implementation of the k-means clustering algorithm was used to classify student academic performance into 3 clusters. Each cluster has an initial centroid that is randomly determined, the centroid changes if each clustering process transfers data to each cluster and changes the centroid to stop if there is no change in the data. Based on 3 attempts to classify 89 student data from semester 1 to 7 there were 89 students from each semester. The data inputted in the form of Absenteeism, Tasks, UTS and UAS Students of the 2015 Informatics Engineering Study Program. The resulting output is in the form of grouping students categorized as groups that are less satisfying, satisfying and very satisfying.after the rapidminer clustering process with k-means, 22.47% of students obtained an increase in academic performance from semester 1 to semester 7.3.37% students experienced a decline in academic performance and 74.15% the rest Fluctuated.