https://github.com/alicezoe/elliptic_insight
Elliptic Insight - Le Wagon Data Science & AI Bootcamp Project
https://github.com/alicezoe/elliptic_insight
anomaly-detection bitcoin data-science machine-learning
Last synced: 2 months ago
JSON representation
Elliptic Insight - Le Wagon Data Science & AI Bootcamp Project
- Host: GitHub
- URL: https://github.com/alicezoe/elliptic_insight
- Owner: alicezoe
- Created: 2025-06-02T09:14:21.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2025-06-10T13:39:25.000Z (about 1 year ago)
- Last Synced: 2025-06-10T14:48:31.291Z (about 1 year ago)
- Topics: anomaly-detection, bitcoin, data-science, machine-learning
- Language: Python
- Homepage:
- Size: 14.6 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Bitcoin Fraud Detection System
## 🎯 Problem Statement
Cryptocurrency fraud costs billions annually.
This project tackles Bitcoin transaction fraud detection using the Elliptic dataset - one of the largest public datasets of real Bitcoin transactions labeled as licit or illicit.
## 🔬 Approach
I implemented and compared multiple machine learning approaches:
- **Traditional ML Models:** [List which ones you used - Random Forest, SVM, etc.]
- **Graph Neural Networks:** Leveraging Bitcoin's transaction graph structure
- **Autoencoders:** For anomaly detection in transaction patterns
## 📊 Results
[Add your key findings - accuracy scores, which model performed best, any insights about fraud patterns]
## 🛠️ Tech Stack
- Python, Pandas, NumPy
- Scikit-learn, TensorFlow
- Graph analysis libraries
- Data visualization tools
## 🚀 How to Run
1. Clone the repository
2. Install requirements: `pip install -r requirements.txt`
3. [Add specific steps to run your analysis]
## 💡 Key Insights
[Add 2-3 bullet points about what you learned about fraud detection or the effectiveness of different approaches]