K-means method for clustering learning classes

Abstract

Learning class is a collection of several students in an educational institution. Every beginning of the school year the educational institution conducts a grouping class test. However, sometimes class grouping is not in accordance with the ability of students. For this reason, a system is needed to be able to see the ability of students according to the desired parameters. Determination of the weight of test scores is done using the K-means method as a grouping method. Iteration or repetition process in the K-means method is very important because the weight value is still very possible to change. Therefore, the repetition process is carried out to produce a value that does not change and is used to determine the ability level of students. The results of the class grouping test scores affect the ability of students. Application of K-means method is used in building an information system grouping student admissions in an educational institution. Acceptance of students will be grouped into 3 groups of learning classes. The results of testing the system that applies K-means method and based on data on the admission of prospective students from educational institutions have very high accuracy with an error rate of 0.074.