Analisis Klaster Partitioning Around Medoids dengan Gower Distance untuk Rekomendasi Indekos (Studi Kasus: Indekos di Sekitar Kampus UPNVJT)

Sahat Renaldi. S (Universitas Pembangunan Nasional “Veteran” Jawa Timur, Indonesia)
Dwi Arman Prasetya (Universitas Pembangunan Nasional “Veteran” Jawa Timur, Indonesia)
Amri Muhaimin (Universitas Pembangunan Nasional “Veteran” Jawa Timur, Indonesia)

G-Tech : Jurnal Teknologi Terapan
Vol 8 No 3 (2024): G-Tech, Vol. 8 No. 3 Juli 2024

In choosing a boarding house, many criteria are considered by prospective tenants. This situation requires an analytical approach that can assist individuals in finding a boarding house while taking into account their preferences. This study aims to develop a recommendation system using K-Prototype and Partitioning Around Medoids (PAM) with Gower Distance. The PAM method with Gower Distance performed better, achieving a Silhouette index of 0.45, and successfully clustered boarding houses into two categories: standard and exclusive. The recommendation system is based on Gower distance similarity. User Acceptance Test (UAT) results showed a score of 70%, indicating that the system is generally well-received and acceptable to users.