The determination of outstanding students is based on different criteria, depending on the type of achievement that is to be measured. At SMK Migas Cepu, this assessment is typically based on the highest academic score from the class promotion exam. However, this method is considered less accurate and problematic in terms of grouping students. To address this issue, a clustering method using the K-Means algorithm can be applied. The purpose of this research is to build a K-Means model to determine outstanding students. The data used in this study comes from the report card ledger of class XI Machine A and B for the year 2022, which includes 71 students at SMK Migas Cepu. The RapidMiner tool was used to build the K-Means model and cluster the data based on student characteristics. The first test conducted using Excel resulted in two clusters: 35 outstanding students and 36 non-outstanding students. Meanwhile, the second test using the RapidMiner model produced two clusters with a distribution of 26 outstanding students and 45 non-outstanding students.
