okothjosh/matatu_ml

final year school project on a machine learning system that predicts demand and pricing of matatus in Kenya # matatu_ml Final year school project on a machine learning system that predicts demand and pricing of matatus in Kenya ## 🚌 Project Overview This project develops a comprehensive machine learning system that: - **Predicts demand** for matatu (mini-bus) services in Kenya - **Optimizes pricing** strategies based on demand patterns and market conditions - **Analyzes surge pricing** opportunities across different routes ## 📊 Features - Data-driven insights from real matatu operations - Advanced ML models (XGBoost, Neural Networks) - Demand forecasting and trend analysis - Revenue optimization through surge pricing simulation - Interactive web dashboard (Streamlit) ## 🛠️ Technologies Used - **Python** - Core programming language - **Pandas & NumPy** - Data manipulation and analysis - **Scikit-learn** - Machine learning algorithms - **XGBoost** - Gradient boosting models - **TensorFlow/Keras** - Deep learning models - **Plotly** - Interactive visualizations - **Streamlit** - Web application framework ## 📁 Project Structure ``` matatu_ml/ ├── 01_data_ingestion.ipynb # Data collection and loading ├── 02_preprocessing.ipynb # Feature engineering and cleaning ├── 03_model_training_evaluation.ipynb # Traditional ML models ├── 04_XGBoost_model_training.ipynb # Advanced gradient boosting ├── 05_surge_simulation.ipynb # Pricing simulation and analysis ├── app.py # Streamlit web application ├── requirements.txt # Python dependencies └── data/ # Dataset and outputs ``` ## 🚀 Quick Start ### Prerequisites - Python 3.8+ - pip or conda ### Installation 1. Clone the repository: ```bash git clone github.com cd matatu_ml ``` 2. Create a virtual environment: ```bash python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate ``` 3. Install dependencies: ```bash pip install -r requirements.txt ``` ### Running the S …