Movie recommendation using link prediction

Abstract

Link prediction is an important task for analyzing movie recommendation which also has applications in other domain like, information retrieval and bioinformatics. Proximity measure quantify the closeness or similarity between nodes in movie rec ommendation and form the basis of a range of applications in social sciences different quality based movie, information about user’s choice, networking and connecting . Recommendation can be effective of link prediction sub-process, with unique nodes (users and items) and connections (similar user/item relationships and user/item interections). Through specific methods and techniques, the recommending systems try to identify the most appropriate items, such as types of information and good and propose the closest to the user’s tastes. One of the easiest and most under standable and authorisation for locating people with the same preferences in the recommendation systems is mutual filtering that provides active performance data based on the ranking of a segment of people. In this model, the process is subject to scalability, with a growing number of users and movies. Across the other hand, when there is little information available on the ratings, it is essential to promote the system’s performance. This study proposes an efficient dynamic graph prediction using link algorithm to predict the user’s choice and recommended the movie based on that link prediction. Temporal information offers link occurrence behavior in the dynamic network, while community clustering shows how strong the connection between two individual nodes is, based on whether they share the same community. These model and methods have achieved higher prediction of recommending. We got better prediction by implementing Jaccard coefficient into methods. Furthermore, in the future, we will use more algorithms to improve the recommending based on the rating of the movies by sorting them for the users.