Music is an inseparable part of everyone's life. Many people listen to music but with different preferences because there are so many different types of music available. Many music streaming platforms compete to make song recommendations that suit their users' preferences but it is still difficult to group the music in them. This study aims to analyze music using the K-Means Clustering algorithm, an unsupervised machine learning method, to group songs based on their features such as tempo, tone, and other elements. This research was conducted in the context of the rapidly growing digitalization of music, where music streaming platforms are increasingly popular and allow for personalization of user preferences. The K-Means algorithm is used to find patterns from various music genres, so that it can provide insight into music trends and listener preferences. This study involves several main stages, including data exploration (Exploratory Data Analysis/EDA), checking for missing values and outliers, and selecting relevant features. Furthermore, the clustering process is carried out using the K-Means algorithm with evaluation through the Elbow and Silhouette methods to determine the optimal number of clusters and assess the quality of clustering. This research is expected to contribute to the development of a better music recommendation system by increasing knowledge in the field of machine learning, especially in the application of the K-Means algorithm for music data clustering.