Aim of the Project

To build an End-to-End Web App using Data Science & Machine Learning to predict whether a Website is either Legitimate or Suspicious or Phishy

Life Cycle of the Project

1. Collected the dataset from Kaggle
2. Performed Random Oversampling to handle the Imbalanced dataset and built an ML model by tuning the Hyperparameters of Support Vector Classifier using GridSearchCV
3. Saved the Best Performing model in a Pickle file
4. Built a Web App using Python at the Backend with Flask API and HTML & Bootstrap serving at the Frontend.
5. Deployed the Web App on 2 Cloud Platforms: Heroku Cloud and Azure Cloud
6. The Web App receives the data from the User Input, makes predictions with the saved ML model and sends a Prediction text indicating whether a Website is either Legitimate or Suspicious or Phishy

Results from the Project

• If the Website is Legitimate

• If the Website is Suspicious

• If the Website is Phishy

Technologies Used

| Python | Sci-kit Learn | Flask | Azure | Heroku | Gunicorn |

| Pickle | Pandas | Numpy | Matplotlib | Seaborn |

Heroku Web App

Azure Web App

GitHub Repository