Competition in the world of technology is growing rapidly, one of which is smartphones. It is undeniable that almost everything from students to adults involves technology, especially smartphones. There are many brands, types of smartphones, and the number of sales is increasing day by day, so recording sales using technology is necessary so that all markets are met. In this research, grouping analysis of smartphone sales data was carried out using the K-Means algorithm. The data used is 26015 data, and the number of clusters used is 3, where the sales data will be grouped into 3 groups/classes. Data processing will be divided into 3 simulations with simulated train data and test data 80% and 20%, 70% and 30%, 50% and 50%. Data were evaluated using the Davies Bouldin Index, Silhouette Index, and Calinski Harabasz Index evaluations. The results of the study show that the best results are in simulation 1 (80% data train, and 20% test data) because there are 2 evaluations with optimal results, namely the evaluation of the Davies Bouldin Index and the Silhouette Index, and the final value of cluster 0 is 4110 data, cluster 1 as many as 319 data, and cluster 2 as many as 774 data.