Marketplace Affiliates Potential Analysis Using Cosine Similarity and Vision-Based Page Segmentation.

• Main Authors: Wildan Budiawan, Zulfikar, Mohamad, Irfan, Muhammad, Ghufron, Jumadi, M, Esa, Firmansyah
• Format: Journal
• Language: English
• Published: 2020
• Subjects: T Technology (General)
• Online Access: http://ur.aeu.edu.my/783/1/2018-5900-1-PB.pdf; http://ur.aeu.edu.my/783/

One success factor of an online affiliate is determined by the quality of the content source. Therefore, affiliate marketplaces need to do an objective assessment to retrieve content data that will be used to choose the right product in the appropriate product filter. Usually, the selection is not made using a good and measured system so that the selection of product content is only based on parts that are not in accordance with what is seen or subjective. However, if analyzed using a good and measurable system will produce an objective product content and can have a positive impact on users because the selection is based on factual data. The purpose of this research is to analyze the potential of the affiliate marketplace by combining cosine similarity with vision-based page segmentation. This is a new breakthrough made for optimization to get the best content in accordance with the required criteria. This work will produce a number of product recommendations that are appropriate for publication and then made use of for comparison that matches the required criteria. At the limited evaluation stage, the performance of the proposed model obtained satisfactory results, in which 5 queries tested were all as expected