A Content Based Product Recommendation Approach

In this study, a content-based recommendation approach is proposed. It utilizes the preprocessed 245 top movie summaries of IMDB and favorite genres user elicited with questionnaire method then, recommends potential products -from product pool- that can “like”. For testing; test dataset consists real from Amazon.com was created, Web application uses proposed leads users to evaluate results designed developed. 52 volunteered subjects attended test. The subject examined graded each 10 displayed. Grading based on five-level Likert-type scale “Not at all” (0%), “Slightly” (25%), “Moderate” (50%), “Very” (75%), “Extremely” (100%). possible say are moderately liked products. When evaluations categorized in two categories as “liked” “disliked”, it ~78.65% This could be integrated into e-commerce applications like for recommending