Movie Recommender System Based on Percentage of View

with ever-increasing data on the internet, finding the desired content has become harder and that is why recommender systems' role is very important in business. As a specific example, media service providers, such as Netflix, can improve their service by recommending desirable content to each user. Most of the previous studies used explicit feedback of users, through likes and dislikes, to recommend items to their customers. However, in many cases, there is not much explicit feedback about items which cripples typical recommender systems to operate efficiently and provide accurate recommendation. In this paper, a percentage of view approach is proposed to find relevant movies for customers. To prove the effectiveness of the approach, first, it is shown that this feature can be a good indicator of users' like and dislike. Then the best approach is determined and used in a recommender system for Namava, a media service provider. Then the performance of this recommender system is compared to a random recommender system and the effectiveness of the approach is shown.