Cybercrime Predictive Analytics System

This project contains a fully developed predictive analytics framework that analyzes cybercrime complaint data to forecast potential cash withdrawal locations used by cybercriminals.

Project Structure

The project is divided into two parts:

1. backend/: Python Flask API server running the Machine Learning model.
2. frontend/: React + Vite frontend application with a predictive dashboard and interactive map.

Setup Instructions

1. Start the Backend

1. Open a terminal and navigate to the backend folder:

   cd backend

2. Create and activate a virtual environment (optional but recommended):

   python -m venv venv
   venv\Scripts\activate

3. Install the Python dependencies:

   pip install -r requirements.txt

4. Run the Flask server:

   python app.py

   Note: The first time it runs, app.py will automatically generate 1000 mock records in data/ and train a Random Forest model in models/rf_model.pkl. This may take a few seconds.

The backend will be accessible at http://localhost:5000.

2. Start the Frontend

1. Open a new terminal and navigate to the frontend folder:

   cd frontend

2. Install the Node dependencies:

   npm install

3. Run the Vite development server:

   npm run dev

4. Open your browser and navigate to the http://localhost:5173 (or the URL provided in the terminal terminal output).

Technologies Used

• Backend: Python, Flask, Scikit-learn, Pandas
• Frontend: React.js, Vite, React-Leaflet, Axios, Vanilla CSS Variables (Dark theme)