Web Series Recommendation System Using Machine Learning

Anirban Mitra, Loknath Roy, Rupam Ghosh, Debranjan Pal, Sudipta Roy, Narayan C. Debnath, Soumya Sen

Abstract: Nowadays, the web series has turned out to be part and parcel of viewers entertainment world. At present when people can’t find out so much time from their busy schedule to take a correct decision over enormous options and happiness depends on others suggestions, they prefer to select or purchase a new product based on the feed-back from other users who have used a similar or similar type of products. Instead of doing these time-consuming tasks manually, a recommender system needs to be implemented to do all these tasks automatically. In this project, a Machine learning-based web Series recommendation system has been designed to suggest web series to the users which they have not watched yet. In this recommendation system at first, some parameters have been taken as features of tagging, and all the elements have been mapped with their respective id created separately for each of the selected para-meters and using tagging, we have got different classes for a list of web series. After tagging all the features of web series have been mapped and a recommendation system has been used to recommend unseen but preferable movies to the users. Different types of analysis on parameters which are used in our system and their results and different graphs prove the robustness of our recommendation system.