Clustering Tourism Destinations in Denpasar City in 2023 Based on Visitor Preferences Using K-Means and DBSCAN Clustering Methods
Abstract
In the digital era, the increasing number of tourist destinations in Denpasar City poses challenges for effective and sustainable management. This study develops a clustering system for tourist destinations in 2023 based on visitor preferences using K-Means and DBSCAN methods. Data on tourist visits and destination facilities, sourced from the Denpasar City Tourism Office, were processed through preprocessing steps, including missing data imputation and feature standardization. K-Means clusters destinations based on proximity to cluster centroids, while DBSCAN excels in detecting density-based clusters and outliers. Evaluation using the Elbow Method and Silhouette Score indicates that K-Means is more optimal for forming a specific number of clusters, with Silhouette Scores of 0.654 for foreign tourists, 0.614 for domestic tourists, and 0.579 for combined tourists. Conversely, DBSCAN performs better in handling irregular data distributions and identifying outliers, with Silhouette Scores of 0.681 for foreign tourists, 0.578 for domestic tourists, and 0.529 for combined tourists. The agreement rate between the two methods reaches 86.7% for foreign tourists, 80.0% for domestic tourists, and 83.3% for combined tourists. The results are visualized through an interactive dashboard mapping cluster distributions, enabling the Tourism Office to analyze visit patterns and formulate targeted, efficient strategies for destination development
References
[2] N. Putu et al., “Promosi Destinasi Pariwisata Dan Budaya Kota Denpasar Melalui Aplikasi Permainan,” SENADA (Seminar Nas. Manajemen, Desain dan Apl. Bisnis Teknol., vol. 5, pp. 314–320, 2022, [Online]. Available: https://eprosiding.idbbali.ac.id/index.php/senada/article/view/687
[3] L. Maulida et al., “PENERAPAN DATAMINING DALAM MENGELOMPOKKAN KUNJUNGAN WISATAWAN KE OBJEK WISATA UNGGULAN DI PROV. DKI JAKARTA DENGAN K-MEANS,” J. Inform. Sunan Kalijaga), vol. 2, no. 3, pp. 167–174, 2018.
[4] S. Astiti and R. Harman, “Pengelompokan Destinasi Wisata di Batam Berdasarkan Daya Tarik dan Fasilitas Menggunakan Metode K-Means Clustering,” vol. 5, no. 4, pp. 2005–2012, 2024.
[5] A. A. MAHARDIKA, E. N. KENCANA, I. K. G. SUKARSA, K. JAYANEGARA, I. L. WIJAYAKUSUMA, and I. W. SUMARJAYA, “Klasterisasi Karakteristik Wisatawan Mancanegara Menggunakan Metode K-Means Clustering,” E-Jurnal Mat., vol. 12, no. 2, p. 140, 2023, doi: 10.24843/mtk.2023.v12.i02.p411.
[6] H. Gunawan and V. Purwayoga, “Data Mining Menggunakan Algoritma K-Means Clustering Untuk Mengetahui Potensi Penyebaran Virus Corona Di Kota Cirebon,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 11, no. 1, pp. 1–8, 2022, doi: 10.32736/sisfokom.v11i1.1316.
[7] N. Lusianah, A. Irma Purnamasari, and B. Nurhakim, “Implementasi Algoritma K-Means Dalam Pengelompokan Jumlah Wisatawan Akomodasi Di Jawa Barat”.
[8] K. Gustipartsani, N. Rahaningsih, R. D. Dana, and I. Y. Mustafa, “DATA MINING CLUSTERING MENGGUNAKAN ALGORITMA K-MEANS PADA DATA KUNJUNGAN WISATAWAN DI KABUPATEN KARAWANG,” 2023.
[9] L. F. Marini and C. D. Suhendra, “Penggunaan Algoritma K-Means Pada Aplikasi Pemetaaan Klaster Daerah Pariwisata,” J. Media Inform. Budidarma, vol. 7, no. 2, p. 707, 2023, doi: 10.30865/mib.v7i2.5558.
[10] C. Mei Hellyana, “Penerapan Algoritma K-Means Terhadap Kunjungan Wisatawan Asing Di Hotel Berbintang di Indonesia,” J. Sains dan Manaj., vol. 11, no. 1, pp. 67–77, 2023.
[11] Y. Syawali, M. Haikal, H. Rangkuti, and K. A. Mayadi, “PENERAPAN ALGORITMA DBSCAN UNTUK ANALISIS DEMOGRAFIS dan PENGELUARAN PELANGGAN MALL”.
[12] R. Wulandari and W. Yustanti, “Analisis Text Clustering Kebijakan Pembukaan Daerah Wisata pada Masa Pandemi Berbasis Densitas Spasial (DBSCAN),” J. Emerg. Inf. Syst. Bus. Intell., vol. 3, no. 2, pp. 1–10, 2022.
[13] M. Adi, P. Firdaus, and Y. Yamasari, “Implementasi Data Mining Untuk Pengelompokan Kunjungan Wisata Di Kabupaten Mojokerto,” J. Informatics Comput. Sci., vol. 06, 2024.