Migration Forecasting Project

A full-stack application for forecasting city-to-city migration patterns using time-series analysis and machine learning. The system enables scenario-based simulations (e.g., Spring Festival, COVID-19) and provides interactive visualizations of migration flows.

Overview

This project combines time-series forecasting models (XGBoost) with interactive geospatial visualization to predict and analyze inter-city migration patterns. Users can explore different scenarios and visualize migration flows through an intuitive web interface powered by Kepler.gl.

System Architecture

The project is organized into four main components:

• Frontend: React + TypeScript web application with Kepler.gl for interactive map visualizations
• Backend: FastAPI REST API handling data requests and forecasting operations
• Model: XGBoost-based time-series forecasting models and two-stage method with scenario simulation capabilities
• Data: City-to-city migration datasets with geographic coordinates

Getting Started

Prerequisites

• Python 3.8+ with pip
• Node.js 16+ with npm

Backend Setup

1. Install Python dependencies:

   pip install -r requirements.txt

2. Start the FastAPI server:

   cd backend
   uvicorn main:app --reload

   The API will be available at http://localhost:8000

Frontend Setup

1. Install Node.js dependencies:

   cd frontend
   npm install

2. Start the development server:

   npm run dev

   The frontend will be available at http://localhost:5173

Running the Application

1. Ensure both backend and frontend servers are running
2. Open http://localhost:5173 in your browser
3. Select scenarios, date ranges, and geographic filters to explore migration forecasts

Project Structure

migration-project/
├── backend/          # FastAPI application
├── frontend/         # React + TypeScript application
├── prediction_model/ # XGBoost forecasting models & two stage method 
├── requirements.txt  # Python dependencies
└── README.md        # This file

License

This project is intended for coursework or demonstration purposes.