<![CDATA[This study aims to compare the performance of the K-Means and K-Medoids algorithms in clustering tourist destinations in Bali Province based on multidimensional characteristics, including rating, number of reviews, latitude, longitude, category, and district/city. The dataset used comes from Kaggle with 1,000 tourist destination data that have gone through a preprocessing process in the form of data cleaning, feature selection, normalization, and logarithmic transformation. The optimal number of clusters is determined using the Elbow Method in the range of K = 2 to K = 10, while the quality of the clusters is evaluated using the Silhouette Score, Davies-Bouldin Index (DBI), and Mean Squared Error (MSE). The results show that the optimal number of clusters is K = 10. K-Means produces a Silhouette Score of 0.2078, a DBI of 1.2714, and an MSE of 2.2764, thus showing better performance than K-Medoids. This study contributes in the form of a comparative evaluation of the two algorithms and recommendations for clustering methods that are more suitable for Bali tourist destination data. The research results can also support decision making in the management and development of the tourism sector.]]>
Copyrights © 2026
