POLA AKSES PENGUNJUNG TOKO ONLINE MENGGUNAKAN WEIGHTED GRAPH WEB USAGE MINING (Studi Kasus Toko Koi Online)

• Main Authors: , Helmy, , Ir. Paulus Insap Santosa, M.Sc., Ph.D.
• Format: Theses and Dissertations NonPeerReviewed
• Published: [Yogyakarta] : Universitas Gadjah Mada 2013
• Subjects: ETD
• Online Access: https://repository.ugm.ac.id/125754/; http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=65930
• Institution: Universitas Gadjah Mada

The increase of online store growth is directly proportional with number of web usage data produced. Web Usage Mining can extract useful information based on web usage data. Some useful information for online store owner are frequently accessed webpages and items that attrack visitors. Nowadays, online store owner discover this information when visitors made a transaction. It complicates online store owner to find out visitors interest in items. This research aims to help online store owner discover visitor access patterns. Based on these patterns, online store owner can discover frequently accessed webpages and items that attrack visitors. This research uses Weighted Graph Web Usage Mining method to extract online store visitor access pattern. This method covers web usage data on client level use real time AJAX interface, pre-processing to generate traversal database real time and Weighted Frequent Patterns Mining method for pattern discovery. Result shows that Weighted Graph Web Usage Mining can deliver information about frequently accessed webpages and items that attrack visitors in certain periods based on visitor access patterns. This method has average accuration of 65.5%.