Enhanced Movie Recommendation using Knowledge Graph and Particle Filtering

In today’s very busy world, recommendation systems are becoming increasingly crucial. In a 24-hour period, people are always pressed for time because of the many activities they must do. Deshalb, the Movie recommendation systems are vital, as they help cinephiles find the finest movies to watch without having to waste their cognitive resources which are limited. This project aims to propose a movie recommendation system using the concept of knowledge graph and particle filtering. While every existing movie recommendation system depends on machine learning and clustering algorithms. This research work proposes a novel movie recommender system that operates directly on the database and is extremely efficient by utilizing the expressive potential of Knowledge Graphs and provides the user with the best recommendations. Using particle filtering and a knowledge graph database, this movie recommendation system provides the user with the best suitable movies depending on numerous parameters such as the user’s favourite Directors, genre, etc. Unlike other systems, this recommendation system does not keep track of the browser history for future recommendations.