Download PDFOpen PDF in browser

Movie Recommendation System Using Machine Learning

EasyChair Preprint no. 10999

6 pagesDate: September 30, 2023


The exponential growth of digital content has led to an overwhelming abundance of movies and TV shows, making it increasingly challenging for viewers to discover content that aligns with their preferences. To address this issue, the Movie Recommendation System based on Machine Learning has emerged as a promising solution. This abstract provides an overview of such a system.


In this research paper we are going to develop a model to recommend movies based on item-based filtering and not on user based. Most of the movie recommendations used by organizations are using user based collaborative filtering but this limits us to recommend movies when we get a sufficient data of user to find their behavior.


Item based filtering usually maps the item with one another using some criterion or model and here we will use vectorization for that. This model will map all the vectors which is here referred as movies on a single point and will work on that to find angle between them and the most similar movies will be the one with smallest angle between them.


Key components of the system include data collection and preprocessing, feature engineering, and model training. Item-based collaborative filtering, are used to establish relationships between users and movies based on their interactions. Content-based filtering analyzes movie attributes like genre, actors, summary, and user preferences to create content-based recommendations. Hybrid methods combine collaborative and content-based filtering to enhance recommendation quality.


In conclusion, the Movie Recommendation System Based on Machine Learning leverages advanced algorithms to provide users with personalized and engaging movie recommendations, addressing the challenge of content discovery in the digital age. This system not only enhances user satisfaction but also benefits content providers by increasing user engagement and retention.

Keyphrases: collaborative filtering, Movie Recommendation, Natural Language Processing, personalized recommendation, Recommendation System, User preferences., Vectorization

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Aayush Khanna and Kartik Arya},
  title = {Movie Recommendation System Using Machine Learning},
  howpublished = {EasyChair Preprint no. 10999},

  year = {EasyChair, 2023}}
Download PDFOpen PDF in browser