Recommender System for Generic User Preferences for Online Content

Abstract

Most recommendation systems have been increasingly in development ever since the major content expanse on the World Wide Web and these recommendation systems serve as a way to handle the rate at which content is uploaded to the internet in such a very short period of time. Recent statistics conducted strongly suggest that almost 300 hours of video and content is uploaded to YouTube almost every minute, and the major amount of vast resources that are available for use to the users make it a challenge to find the exact content or even the best content that they often desired. The spread of high-bandwidth internet and the major increased saturation of internet users has brought upon the big data era, and it has been brought to light that certain high-end content providers who cater a large number of users and subscribers, enlist to using their own forms of custom recommendation systems to sort through the near unlimited number of videos in their databases in order to allow their users better access to their content.