claws-lab/jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"
This project helps businesses and researchers understand and predict how entities like users, items, or accounts behave and interact over time within dynamic networks. It takes a history of interactions (who interacted with what, when, and any associated features) and outputs predictions about future interactions or changes in an entity's state. People in e-commerce, social media, finance, or education who need to make recommendations, detect fraud, or predict churn would find this useful.
414 stars. No commits in the last 6 months.
Use this if you need to predict future interactions between entities or detect when an entity's behavior changes, such as predicting customer churn or fraudulent activities.
Not ideal if your data doesn't involve temporal interactions or if you only need static representations of entities that don't change over time.
Stars
414
Forks
84
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/claws-lab/jodie"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
eliorc/node2vec
Implementation of the node2vec algorithm.
mims-harvard/decagon
Graph convolutional neural network for multirelational link prediction
mims-harvard/nimfa
Nimfa: Nonnegative matrix factorization in Python
ferencberes/online-node2vec
Node Embeddings in Dynamic Graphs
mims-harvard/Raindrop
Graph Neural Networks for Irregular Time Series