Application of Data Mining Using the K-Means Clustering Method in Grouping Value Data at YKPP PENDOPO High School to Determine Ipa and Ips Majors.

Abstract

With the development of science and technology in the field of education, technology plays an important role in supporting the learning system in the 2013 curriculum. This study aims to determine the number of students who will enter science and social classes in accordance with their majors in order to develop their potential and improve students' academic grades, with that the author needs data on student grades at YKPP PENDOPO High School and is expected to help make decisions by applying the k-means clustering method. The k-means algorithm is to divide the data then group it into several clusters that have data characteristics and divide each cluster based on differences in character between clusters. Clustering is a process where grouping and dividing into several data sets to form similar patterns and grouped in the same cluster and separate themselves by forming different patterns in different clusters. The results of the tests carried out in the application of data mining with the k-means clustering method in grouping student score data for the majors of science and ips, it can be concluded that k-means can be used to group the determination of majors with optimal results and does not take a long time. The test also uses Rapid Miner tools and uses secondary data, where this data contains report card values at the time of registration. Based on the test results show that, among the 58 students enrolled in YKPP Pendopo High School, there are 15 students enrolled in social studies class 1 in Cluster 0, 11 students enrolled in science class 1 in Cluster 1, 15 students enrolled in social studies class 2 in Cluster 2, and 13 students enrolled in science class 2 in Cluster 3.