Recommendation system for video streaming websites based on user feedback

Abstract

Now a days world business �organizations are mostly focused in e-commerce for enlightening their business as well as supporting their users. In the modern era, vast amount of information is generated from the internet which is open to the users. Recommendation system is midway between internet and user which expects user interests. This paper primarily focusing on developing the recommendation system for �video streaming sites. The recommendation engine mainly works on content based, collaborative based filtering algorithms. But both has limitations in their own way. The content-based filtering has a shortcoming that, it restricts recommendations of the items that are of same category. Whereas in the collaborative-based filtering algorithm, it doesn’t recommend items based on the user’s past behavior. So, this system is developed using a hybrid algorithm to overcome the problems of above two algorithms by retrieving feedback from the users and calculating semantic factor from the feedback to improve the efficiency of the recommendation system. So that lets companies can better understand the user, make available personalized stores, and increases the satisfaction of the customer and their loyalty.