https://github.com/rayyan9477/anomaly-detection-in-cloudwatch-traffic-data
This project focuses on detecting anomalies in CloudWatch traffic data using machine learning techniques. The primary goal is to identify potential web attacks by analyzing traffic patterns. The project leverages the Isolation Forest algorithm for anomaly detection and includes comprehensive data preprocessing steps.
https://github.com/rayyan9477/anomaly-detection-in-cloudwatch-traffic-data
anomaly-detection data-science machine-learning sklearn
Last synced: 5 months ago
JSON representation
This project focuses on detecting anomalies in CloudWatch traffic data using machine learning techniques. The primary goal is to identify potential web attacks by analyzing traffic patterns. The project leverages the Isolation Forest algorithm for anomaly detection and includes comprehensive data preprocessing steps.
- Host: GitHub
- URL: https://github.com/rayyan9477/anomaly-detection-in-cloudwatch-traffic-data
- Owner: Rayyan9477
- License: mit
- Created: 2024-09-03T14:55:18.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-04T18:12:15.000Z (almost 2 years ago)
- Last Synced: 2025-03-16T07:23:07.092Z (over 1 year ago)
- Topics: anomaly-detection, data-science, machine-learning, sklearn
- Language: Jupyter Notebook
- Homepage:
- Size: 3.93 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
- License: LICENSE
Awesome Lists containing this project
README
# Anomaly Detection in CloudWatch Traffic Data
## Summary
This project focuses on detecting anomalies in CloudWatch traffic data using machine learning techniques. The primary goal is to identify potential web attacks by analyzing traffic patterns. The project leverages the Isolation Forest algorithm for anomaly detection and includes comprehensive data preprocessing steps. Visualization tools such as Matplotlib, Seaborn, and Plotly are used to present the results effectively.
### Techniques Used:
- **Data Preprocessing**: Handling datetime features and calculating duration.
- **Anomaly Detection**: Using Isolation Forest from scikit-learn.
- **Data Visualization**: Matplotlib, Seaborn, and Plotly for plotting results.
- **Evaluation**: Confusion matrix for performance evaluation.
## How to Run
1. **Clone the repository**:
```sh
git clone https://github.com/Rayyan9477/Anomaly-Detection-in-CloudWatch-Traffic-Data
cd Anomaly-Detection-in-CloudWatch-Traffic-Data
```
2. **Install the required packages**:
```sh
pip install -r requirements.txt
```
3. **Run the application**:
```sh
python app.py
```
## Significance and Use Case
This project is significant for cybersecurity applications, particularly in monitoring and securing web traffic. By identifying anomalies, it helps in early detection of potential web attacks, thereby enhancing the security posture of web applications. The techniques used can be applied to various domains requiring anomaly detection in time-series data.
## Video Demostration
[Video Demonstration](https://github.com/Rayyan9477/Anomaly-Detection-in-CloudWatch-Traffic-Data/blob/main/video.mp4)
## Technologies Used
- **Programming Language**: Python
- **Libraries**: pandas, scikit-learn, matplotlib, seaborn, plotly
## Contact
- **Email**: rayyanahmed265@yahoo.com
- **LinkedIn**: [Rayyan Ahmed](https://www.linkedin.com/in/rayyan-ahmed9477/)
- **More Work**: [Rayyan9477](https://github.com/Rayyan9477)