S. Priyanka1, P. Saravanan1*, V. Indragandhi2 and V. Subramaniyaswamy1
1School of Computing, SASTRA Deemed University, Thanjavur, India
2School of Electrical Engineering, Vellore Institute of Technology, Vellore, India
A recommendation process is usually the most commonly used form of commercial website. The custom recommender method is of vital importance in modeling users’ choice of movies based on their previous interest. In today’s internet apps, recommender services play a crucial role. However, the existing Deep Learning (DL) approaches have some limitations, which have a negative impact on the efficiency of the suggestion models. This paper provides an innovative deep learning architecture to improve filtering results in recommender systems. This methodology proposes new movies for users based on individual and related tastes. By studying user trends of film watching, we offer a technique of anticipating and suggesting a film. The similarity between any set of users is estimated using movie rating information and review data. Further we classified the user with similar film preferences and analysed the user group’s consumption behavior to increase forecast accuracy by factoring the change in preferences over time. As films are an important source of entertainment, we have proposed a Recommender System (RS) in this work. Collaborative filtering and content-based ...