In this project, I've unleashed the power of collaborative filtering to recommend movies based on user similarity. Using Jupyter Notebook and the magic of Python libraries, I've created a system that thinks like a movie buff. Want to watch something that resonates with your taste? This system's got you covered!
Creating the core of collaborative filtering, the interaction matrix is a matrix of dreams (or ratings!). It represents every user's relationship with movies.
- Task: Are we dense enough? Calculating the sparsity of the interaction matrix.
Finding your movie-taste twins by calculating similarity among users.
- Task: Using cosine similarity to find user buddies.
Your personal movie guide tailored to your taste buds.
- Task: Creating a function to:
- Receive a user's ID.
- Find 10 similar users.
- Calculate the top movie picks.
- Serve you the top 10 rated movies.
See the magic happen! Run the function and get recommendations.
- Task: Call the function, sit back, and let the recommendations roll in!
Aiming to serve every movie lover with personalized recommendations.
- A Python application: Enter a User ID and get movie recommendations on the fly!
A dataset filled with ratings and preferences, included in the repository, waiting to guide you to your next favorite movie!
Follow the instructions to set up and run the project locally, and dive into a world of cinematic joy!
Love movies as much as we do? Feel free to contribute by opening issues or submitting pull requests!
[Include information about the license here.]
🎉 Happy Movie Hunting! Grab your popcorn, and enjoy the recommendations! 🎉