uyen1109
/

eth-fraud-gnn-uyenuyen-v3

Text Classification

graph-neural-network

fraud-detection

anomaly-detection

Model card Files Files and versions

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

ETH Fraud Graph Model (v3)

This repository contains artefacts exported from a Colab notebook for Ethereum fraud detection.

Contents

pytorch_model.bin (+ model_config.json) — GNN weights (if trained in session).
prob_criminal.npy — per-node probabilities (GraphSAGE or fallback).
node_scores*.csv — scores with labels/probabilities.
feature_columns.json — feature order for inference.
Graph/Viz: edges_all.csv, nodes_features.csv, *.gexf, *.png.

Quick use (sklearn anomaly example)

from huggingface_hub import hf_hub_download
import json, joblib, pandas as pd

repo_id = "<your-username>/eth-fraud-gnn-uyenuyen-v3"
cols = json.load(open(hf_hub_download(repo_id, filename="feature_columns.json")))
# X = pd.DataFrame(...)[cols]
# iso = joblib.load(hf_hub_download(repo_id, filename="iso_model.joblib"))
# scores = -iso.score_samples(X)

Downloads last month: -; Downloads are not tracked for this model. How to track

Space using uyen1109/eth-fraud-gnn-uyenuyen-v3 1