IMPLEMENTASI K-MEANS CLUSTERING PADA DATA PENGELOMPOKAN PENDAFTARAN MAHASISWA BARU (STUDI KASUS UNIVERSITAS ABDURRAB)

Abstract

Facing the complex dynamics of freshman enrollment, the k-means clustering method was introduced as the main approach. The focus is on Abdurrab University, where various attributes of prospective students are investigated, including gender, parental education, parental income, hometown, province, age, and choice of study program. With the k-means clustering algorithm, the purpose of the study is to uncover the underlying patterns of preferences and characteristics of new student groups. The results of this study provide in-depth insight into the factors that influence the decision to admit new students in the campus environment of Abdurrab University. In this study Davies-Bouldin Index (DBI) was used as a method to determine the optimal number of clusters, the lowest DBI value was 1.5 which occurred in 8 clusters. This shows that 8 clusters is the optimal number of clusters for data that has been transformed and is ready for k-means clustering. After carrying out the clustering process with the K-Means method which involves the formation of 8 clusters, to show patterns and insights from the clustering results, there are two ways used in this study, first make a heatmap of the correlation of features displayed, information can be obtained about the relationship between variables. The correlation value ranges from -0.4 to 1.0 where positive values indicate a positive correlation and negative values indicate a negative correlation. A positive correlation means that if the value of one variable increases, then the value of the other variable also tends to increase. Conversely, negative correlation means that if the value of one variable increases, then the value of the other variable tends to decrease.