MOVIEMATE: MOVIE RECOMMENDATION SYSTEM
Vedant Wankhede
School of Science,
G H Raisoni University, Amravati, India
Vedantwankhede206@gmail.com
Atharva Agnihotri
School of Science,
G H Raisoni University, Amravati, India
atharvaagnihotri18@gmail.com
Dr. Suman Sengupta
School of Science,
G H Raisoni University, Amravati, India
sengupta_suman@hotmail.com
Received on: 14 May ,2024 Revised on: 04 June ,2024 Published on: 27 June ,2024
Abstract— Nowadays, recommendation systems have revolutionized the way we search for things of interest. These systems employ an information filtering approach to anticipate user preferences. Commonly applied in areas such as books, news, articles, music, videos, and movies, recommendation systems play a pivotal role. In this study, we introduce MOVIEMATE, a movie recommendation system. Using content-based approach, MOVIEMATE examines information provided by users to recommend movies customized to their individual preferences. MOVIEMATE streamlines the movie selection process, leveraging the collective movie experiences of other users to efficiently deliver personalized recommendations. Developed in Python using Jupyter Notebook and Streamlit, this system harnesses various types of user data, item information, and past transactions stored in dedicated databases to generate recommendations. Navigating through these recommendations, users can effortlessly discover movies that align with their preferences.
Keywords – recommendation system, recommender system, movies, Content-based filtering
DOI Link – https://doi.org/10.69758/CKKV2558
Download