MOVIE MAGIC: DEVELOPING A PERSONALIZED RECOMMENDATION SYSTEM FOR MOVIE ENTHUSIASTS USING MACHINE LEARNING

Abstract

One of the most popular and effective uses of machine learning in business is in recommender systems. This method of information filtering is employed to forecast the user's choice. The most frequently used areas for recommender systems are books, news, articles, music, videos, and movies, among other things. In this essay, we present a collaborative filtering-based movie recommendation system that uses user-provided data to analyse it and then suggests the movies that are most appropriate for the person at hand. The recommended movie list is arranged using a variety of machine learning techniques in accordance with the ratings that previous users have given these films.

Recommender systems are one of the most well-liked and successful applications of machine learning in business. The user's choice is predicted using this information filtering technique. The most often used categories for recommender systems include, among other things, books, news, articles, music, videos, and movies. In this paper, we offer a collaborative filtering-based system for movie selection that analyses user-provided data and then recommends the movies that are best suitable for the user at hand. Using a number of machine learning approaches, the recommended movie list is organised according to the ratings that previous users have given these movies.