<![CDATA[Abstract: This study aims to apply the K-Means algorithm for food product segmentation on the GoFood service based on price and rating variables. The large variety of available products makes data difficult to analyze without systematic grouping, necessitating a method capable of automatically clustering data so that patterns and characteristics become clearer. The K-Means algorithm was chosen for its simple, fast, and effective computational process in dividing data based on distance similarity. The research process includes collecting public datasets, determining the number of clusters, selecting initial centroids, calculating distances using Euclidean Distance, grouping data to the nearest cluster, and iteratively updating centroids until convergence is achieved. Results show that K-Means successfully grouped data into three clusters: Cluster 1 with high price and high rating, Cluster 2 with moderate price and highest rating, and Cluster 3 with low price and very high rating. This study produced a web-based system that automatically processes data and displays clustering results in an easily understandable interface. Keywords: K-Means, Clustering, Segmentation, GoFood, Data Mining Abstrak: Penelitian ini bertujuan menerapkan algoritma K-Means untuk segmentasi produk makanan pada layanan GoFood berdasarkan variabel harga dan rating. Banyaknya variasi produk menyebabkan data sulit dianalisis tanpa pengelompokan sistematis, sehingga diperlukan metode yang mampu mengelompokkan data secara otomatis agar pola dan karakteristik terlihat lebih jelas. Algoritma K-Means dipilih karena memiliki proses perhitungan yang sederhana, cepat, dan efektif dalam membagi data berdasarkan tingkat kemiripan jarak. Proses penelitian meliputi pengumpulan dataset publik, penentuan jumlah cluster, pemilihan centroid awal, perhitungan jarak menggunakan Euclidean Distance, pengelompokan data ke cluster terdekat, hingga pembaruan centroid secara iteratif sampai kondisi konvergen tercapai. Hasil penelitian menunjukkan K-Means berhasil mengelompokkan data ke dalam tiga cluster: Cluster 1 dengan harga tinggi dan rating tinggi, Cluster 2 dengan harga sedang dan rating tertinggi, serta Cluster 3 dengan harga rendah dan rating sangat tinggi. Penelitian ini menghasilkan sistem berbasis web yang mengolah data secara otomatis dan menampilkan hasil clustering dalam tampilan mudah dipahami. Kata kunci: K-Means, Clustering, Segmentasi, GoFood, Data Mining]]>
