RECOMMENDAITON SYSTEM ENGINE FOR MOVIES USING MACHINE LEARNING ALGORITHM (TF-IDF VECTORIZATION)

Abstract

By offering tailored movie recommendations, Movie Recommendation Systems (MRS) are crucial for improving the user experience on streaming services. This research paper proposes and evaluates a Movie Recommendation System utilizing TF-IDF vectorization and cosine similarity. TF-IDF vectorization is used to analyze textual information related to movies, such as plot summaries, cast bios, and genres, in order to give users precise and pertinent suggestions. The similarity between the user's preferences and the movies in the dataset is then calculated using cosine similarity. The results of the study show that the suggested Movie Recommendation System, which makes use of cosine similarity and TF-IDF vectorization, greatly improves user happiness and recommendation accuracy. The developed system offers an effective solution for providing personalized movie recommendations, contributing to the advancement of recommendation systems in the entertainment industry. This study provides valuable insights for streaming platforms to improve their recommendation systems and enhance user engagement. Keywords: Movie Recommendation System, Machine Learning (ML), Natural Language Processing (NLP) TF-IDF Vectorization, Cosine Similarity, Content-Based Filtering, Personalized Recommendations, User Engagement.