<![CDATA[The rapid growth of the smartphone industry has increased market complexity, making objective segmentation more challenging. The objective of this study is to conduct a comparative evaluation of the K - Means and K - Medoids methods in grouping smartphone sales data based on multiple attributes, namely memory, storage, rating, selling price, and original price. Unlike prior studies, this research conducts a direct comparison using the same dataset and multiple evaluation metrics. A systematic data mining approach is implemented through the CRISP-DM framework, covering the stages of data understanding, preprocessing, modeling, and evaluation. The dataset comprises 3,114 smartphone instances, which are grouped into three clusters (k = 3), with performance measured using the Silhouette Coefficient and Davies–Bouldin Index (DBI). Based on the evaluation metrics, K - Medoids exhibits superior cluster cohesion with a Silhouette score of 0.344, exceeding that of K - Means (0.313). Conversely, K - Means demonstrates slightly better separation, as shown by its lower Davies–Bouldin Index (1.061 versus 1.079). Even so, K - Medoids is generally preferred due to its resilience to outliers and its consistency in producing stable clustering outcomes. These findings provide insights to support data-driven decision-making in smartphone market segmentation.]]>
Copyrights © 2026
