AbrahamAdegoke/African-commodities-paradox

# African Commodities Paradox: A Data-Driven Analysis **Analyzing the relationship between commodity dependence and economic volatility across 52 African countries (1990-2023)** A machine learning project investigating why resource rich African economies often experience higher GDP growth volatility the "African Commodities Paradox." **Author:** Abraham Adegoke **Institution:** HEC Lausanne **Course:** Advanced Programming (Fall 2025) --- ## Quick Start ### Prerequisites - Python 3.10 or higher - pip package manager ### Installation & Setup ```bash # 1. Clone the repository git clone github.com cd African-commodities-paradox # 2. Create virtual environment python -m venv venv # 3. Activate virtual environment source venv/bin/activate # Mac/Linux # venv\Scripts\activate # Windows # 4. Install dependencies pip install -r requirements.txt # 5. Run the analysis python main.py # 6. (Optional) Launch interactive dashboard streamlit run app.py ``` --- ## Project Overview ### The Problem Many African economies rely heavily on commodity exports (oil, minerals, agricultural products), yet this dependence often leads to unstable and volatile economic growth. This project builds a data-driven framework to: 1. **Quantify** commodity dependence using a custom Commodity Dependence Index (CDI) 2. **Predict** GDP growth volatility using machine learning 3. **Identify** country clusters with different economic profiles 4. **Analyze** temporal trends and forecast future growth ### Key Research Questions - Does commodity dependence increase GDP growth volatility? - Which factors (governance, inflation, trade openness, investment) are the strongest predictors? - Are there distinct groups of African economies with different risk profiles? - Can good governance overcome the "resource curse"? --- ## Key Results ### Model Performance | Model | R² Score | RMSE | MAE | |-------|----------|------|--- …