Clustering Data Calon Siswa Baru Menggunakan Metode K-Means di Pusat Pengembangan Anak Fajar Baru Cengkareng

Abstract

Clustering is the process of partitioning a set of data objects into subsets known as clusters. K-means is an unsupervised learning algorithm, K-Means also has a function to group data into data clusters. The K-Means algorithm method was chosen because it has a fairly high accuracy of object size, so this algorithm is relatively more scalable and more efficient for processing large numbers of objects. In the world of education, in general, every new school year there will be something called registration of new prospective students, at the Fajar Baru Child Development Center, many prospective students are accepted from 3 years to 5 years old, therefore the authors hope that by using clustering data can easily group data so that it can make it easier to find the necessary data. By using the K-means algorithm method and using the RapidMiner application, it found 80% efficient results in grouping data.