https://github.com/goutamhegde002/creditcard-fraud-detection-streamlit-application-
Creditcard Fraud Detection Streamlit Application with ARIMA and LOF
https://github.com/goutamhegde002/creditcard-fraud-detection-streamlit-application-
anomaly-detection credit-card credit-card-fraud credit-card-fraud-detection credit-card-fraud-detection-using-machine-learning data-processing fraudulent-transactions isolation-forest machine-learning pca pca-analysis real-time-anomaly-detection sckiit-learn streamlit streamlit-community streamlit-webapp visualisation
Last synced: 2 months ago
JSON representation
Creditcard Fraud Detection Streamlit Application with ARIMA and LOF
- Host: GitHub
- URL: https://github.com/goutamhegde002/creditcard-fraud-detection-streamlit-application-
- Owner: goutamhegde002
- License: gpl-3.0
- Created: 2024-08-29T18:34:42.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2024-08-29T18:58:34.000Z (8 months ago)
- Last Synced: 2025-01-08T19:18:28.831Z (4 months ago)
- Topics: anomaly-detection, credit-card, credit-card-fraud, credit-card-fraud-detection, credit-card-fraud-detection-using-machine-learning, data-processing, fraudulent-transactions, isolation-forest, machine-learning, pca, pca-analysis, real-time-anomaly-detection, sckiit-learn, streamlit, streamlit-community, streamlit-webapp, visualisation
- Language: Python
- Homepage: https://creditcardfrauddetectionapp.streamlit.app/
- Size: 20.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Credit Card Fraud Detection App
This project is a Streamlit web application for detecting fraudulent credit card transactions using machine learning models. The app allows users to upload credit card transaction data, preprocess it, and detect anomalies that indicate potential fraud.
## Features
- **Data Upload:** Users can upload their own credit card transaction datasets in CSV format.
- **Data Preprocessing:** The app standardizes the transaction amounts and time features, and applies Principal Component Analysis (PCA) to reduce dimensionality.
- **Anomaly Detection:** Uses machine learning models like Isolation Forest to detect fraudulent transactions.
- **Visualization:** Provides scatter plots to visualize anomalies within PCA-transformed components.
- **Interactive Interface:** Built with Streamlit, allowing easy interaction and visualization of results.
## License
This project is licensed under the GNU General Public License (GPL). You are free to use, modify, and distribute this software under the terms of the GPL.
## How to Use
1. **Upload Data:** Click on "Choose a file" to upload your transaction data.
2. **View Results:** The app will display the processed data, highlighting fraudulent transactions.
3. **Visualization:** Use the built-in visualizations to explore the detected anomalies.
## Deployment
The app is deployed on Streamlit Community Cloud and can be accessed [here](https://creditcardfrauddetectionapp.streamlit.app/).
## Contributing
Contributions are welcome! Please fork the repository and submit a pull request for any improvements or new features.
## Acknowledgments
- **Data Source:** The credit card transaction dataset used in this project is obtained from [Kaggle](https://www.kaggle.com/mlg-ulb/creditcardfraud).
- **Machine Learning Models:** The app leverages models provided by the `scikit-learn` library.
## Contact
If you have any questions or feedback, feel free to reach out via GitHub or email.