A REVIEW ON USER PROFILING USING MACHINE LEARNING ON CONTENT STREAMING PLATFORMS
1Nikita Jain Nahar, 2L.K Vishwamitra and 3*Deepak Sukheja
1 Department of Computer Science and Engineering, Oriental University, Indore, India.
1School of computer Science, IPS Academy, Indore, India.
2Department of Computer Science and Engineering, Oriental University, Indore,India.
3Department of Computer Science and Engineering, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad, India. (*corresponding author)
Abstract. Recommendation systems serve an important role in a variety of areas, including movies, novels, entertainment, including e-business and e- commerce, and they help to improve not only user happiness but also e- business and e-commerce. It recommends various items based on the user’s personally identifiable information, interests, and actions. Nevertheless, since it is a multi- user device, the special characteristics of viewing from content streaming platforms platform has a significant impact on the final and effectiveness of recommendation system. As a result, recommender systems cannot effectively use the predictions and computations of a user’s profile, interests, and behaviors to provide suggestions to the precise viewer(s) viewing an Internet platform. In the context of content streaming platforms platform viewing situations, this article provides a critical evaluation of current recommender systems. It identifies the problems and difficulties, as well as potential research options for addressing them. It also includes qualitative research to verify the emphasized variables that influence recommendations outcomes on content streaming platforms platform. The study indicates that the current recommendation system needs additional development to deal with problems of suggestions on a customized platform, such as content streaming platforms. Improving the recommender system for content streaming platforms may help to increase both audience happiness and conversion rates.
Keywords: First Keyword, Second Keyword, Third Keyword.