A Collaborative, Content-Based Filtering Hybrid Movie Recommender System

Abstract

The popularity of movie recommendation systems, which help consumers select films that align with their preferences, has grown significantly.However, conventional systems often rely solely on user ratings or reviews, which may not accurately capture users' true sentiments towards movies.Finding the content that one likes among the unlimited variety of information that is consumed, such as books, videos, articles, movies, etc., has become a tedious chore in today's digital age.On the other hand, there has been a rise in digital content suppliers who aim to keep as many customers using their service for as long as possible.This led to the development of the recommender system, in which content providers provide recommendations for consumers based on their preferences and tastes.In this essay, we suggest a system for suggesting movies.Due to features like offering a list of movies to users based on their interests or the popularity of the film, movie recommendations are crucial in our social lives.In the following paper, we suggest a method for suggesting movies to users, one that can both suggest movies to new users and to other users who have already viewed them.To gather all the necessary data, including popularity and beauty, which are necessary for recommendations.It mines movie databases.To build a system that makes more accurate movie recommendation, we combine content-based collaborative filtering with hybrid filtering, which combines the outcomes of these two strategies.