NCF Recommender System with PyTorch

Welcome to the NCF Recommender System with PyTorch! In this project, An end-to-end Recommender System using an adjusted version of Neural Collaborative Filtering (NCF) with PyTorch. the model is trained on the MovieLens-1M dataset 🎥, served using FastAPI, hosted on Streamlit 🚀.

🌟 Try it out!

• Website: https://ncf-recsys.streamlit.app/

📓 Notebook on Kaggle

• Notebook: NCF Recommender System with PyTorch: A Deep Dive

🌐 Overview

• Our adjusted architecture of NCF enables the input of the user/item features besides the user/item IDs.

• Quick Reminder: A recommender system is not just a ranking model, but a pipeline consisting of: Items Retrieval, Filtering, Ranking, and Ordering. (Detailed explanation in the notebook)

📚 Project Structure

• streamlit.py: Streamlit app to interact with the model.

• app/:

  • main.py: The FastAPI app to serve the model.
  • model/:
    • utils/:
      • model.py: The NCF model.
      • utils.py: Utility functions for data processing.
      • requests.py: Request class to make API requests.
    • data/: Processed data for inference.
    • weights/: Pretrained models weights for inference.

📖 References

• Neural collaborative filtering Paper
• Medium: Recommender Systems, Not Just a Recommender Models
• MovieLens-1M

💡 Contributing

Contributions are welcome! If you find a typo, want to add more content, or improve something, feel free to open an issue or submit a pull request.

Happy learning! 🚀