This is a movie recommendation system based on collaborative filtering technique. The system is deployed on Streamlit and you can access it via this link.
To use this recommendation system on your local machine, follow these instructions:
Clone the repository to your local machine using the command: git clone https://github.com/Boussairi/Movie-Recommendation-System-using-Machine-Learning-with-Python.git Install the required packages using the command: pip install -r requirements.txt Run the Streamlit app using the command: streamlit run web app.py Access the app via your web browser at the provided link.
When you access the app, you will be presented with a form to select a movie. After selecting a movie, the app will recommend similar movies based on other users' ratings, genres, cast, director and overview.
The recommendation system is based on collaborative filtering technique. It finds similar users based on their rating history and recommends movies to the active user based on the rating history of similar users. The similarity between users is calculated using cosine similarity measure.
The data used for this recommendation system is a subset of the MovieLens dataset. The dataset contains over 100,000 ratings of approximately 8,000 movies from 600 users. The data is preprocessed and cleaned before being used in the model.
This project is inspired by the tutorial from Data Professor on YouTube. The code is modified to fit my personal preferences and to deploy the model on Streamlit.