Optimasi Cluster Pada K-Means Clustering Dengan Teknik Reduksi Dimensi Dataset Menggunakan Gini Index

In K-Means Clustering, the number of attributes a data can affect iterations generated in grouping process. One solutions to overcome these problems is by using reduction technique on dimensions dataset. this study, authors apply Gini Index perform attribute set reduce that have no effect dataset before clustering with Clustering. The used be tested as testing instrument research Absenteeism at work obtained from UCI Machine Learning Repository, 20 attributes, 740 records and 4 classes. results tests indicate comparison Conversional (Without Attribute Reduction) 9 iterations, while obtains totaling 6 iterations. Clustering evaluation was calculated Sum Square Error (SSE). SSE value 1391.613, Index, it 440.912. From proposed method, able percentage errors minimize reducing