A MOVIE RECOMMENDATION SYSTEM USING ML

Deepak Patil , Vrunali Surve , Swara Redij , Ayush Paradke , Shashank Tolye

Movie recommendation system, machine learning, hybrid recommendation, content-based filtering, collaborative filtering, personalized recommendation, Python, Streamlit, Scikit-learn, TMDb API.

This paper is about a movie recommendation system that uses machine learning to suggest movies to people. The system is made up of a few parts, including content-based filtering, collaborative filtering and emotion-based filtering, which all work together to give users personalized movie suggestions. To make this system we first took a dataset and cleaned it up and organized it. Then we used something called feature extraction to make special matrices that show how similar things are to each other.We did all of this work in something called Jupyter Notebook and then we took the data we had prepared and put it into a web application made with Streamlit so people can use it in time.When people use this application they can pick a movie they like. Say how they are feeling and the system will suggest other movies that are similar or that might match their mood. Content-based filtering is when the system suggests movies that're a lot like the one the person picked and collaborative filtering is when the system looks at what other people with similar tastes have liked.We also have emotion-based filtering, which suggests movies that fit the persons mood, like happy or sad movies.The system can also get information about movies from outside like what people think of them what kind of movie it's who is in it and what the poster looks like which makes the experience better for the user.Our system does a job of solving some big problems like making sure the movies are really personalized and that the information is always up to date.It shows that using ways of recommending movies and putting them into a web application that people can interact with can make the whole system work better and be more useful.The results we got from testing the system were good. People seemed to like the suggestions it made. This work is important because it shows how machine learning and web technology can be used together to make things that're useful and work well. The movie recommendation system is an example of this and it can be used in other areas too.The system is made to be practical and to work for a lot of people. It can be used to make other kinds of recommendation systems too.This is a deal because it can help people find things they like and make their lives more fun and interesting. The movie recommendation system is a start and it can be used to make even more things, like it.

Volume 14 Issue 4, April-2026

Pages : b72-b80