khuangaf/PyTorch-Geometric-YooChoose

This is a tutorial for PyTorch Geometric on the YooChoose dataset

50
/ 100
Established

This project helps data scientists and machine learning engineers understand and implement Graph Neural Networks (GNNs) for recommendation systems. It takes raw e-commerce clickstream data, like that from the YooChoose dataset, and demonstrates how to process it to build models that predict user behavior, such as future clicks or purchases. It is ideal for those learning to apply GNNs to sequential or graph-structured user interaction data.

315 stars. No commits in the last 6 months.

Use this if you are a data scientist or machine learning engineer looking for a practical, code-based tutorial to learn how to build and train Graph Neural Networks for e-commerce recommendation tasks.

Not ideal if you are looking for a plug-and-play solution or a pre-trained model for your recommendation system without needing to understand the underlying GNN implementation.

e-commerce recommendation-systems graph-neural-networks clickstream-analysis machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

315

Forks

94

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jun 07, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/khuangaf/PyTorch-Geometric-YooChoose"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.