Hybrid Movie Recommendation System

Abstract

Movie recommendations play a great part in the aspects of our social life. Such a system allows users to recommend a group of films based on their interests or the popularity of the movies. This research was conducted to study different approaches to movie recommendation and discusses a hybrid approach that combines a content-based filter, a collaborative-memory-based filter, and a collaborative-model-based filter. The proposed system aims to reduce the issues with existing movie recommendation systems by enhancing performance. The content-based filter is based on a TF-IDF classifier with cosine similarity. The collaborative-memory-based filter is based on truncated SVD with Pearson correlation. A collaborative model-based filter is based on improved SVD matrix factorization.