ethioel/addis-housing-price-predictor

🏠 Addis Ababa Housing Price Predictor - Synthetic data generation and machine learning pipeline for Ethiopian real estate. Generate realistic housing data based on Jiji.com patterns, train multiple models and predict property prices in ETB. # 🏠 Addis Ababa Housing Price Analysis > **Synthetic housing price dataset generation for Addis Ababa, Ethiopia** > Based on real Jiji.com property listings with realistic distributions --- ## 📊 Overview This project generates **realistic synthetic housing data** for Addis Ababa based on manually extracted property listings from Jiji.com. Since Jiji.com employs anti-bot protection that prevents web scraping, we manually extracted distribution patterns and built a synthetic data generator that preserves statistical properties while allowing scalability. ### 🎯 Key Features | Feature | Description | |---------|-------------| | **15,000+ Records** | Large, realistic dataset for ML modeling | | **10 Sub-cities** | Complete coverage of Addis Ababa | | **5 Property Types** | House, Apartment, Condo, Villa, Studio | | **15+ Features** | Comprehensive property attributes | | **Realistic Distributions** | Based on actual Jiji.com listings | | **Reproducible** | Seeded random generation | ### 💡 Use Cases - 🏗️ **Real Estate Price Prediction** - Train ML models on realistic data - 📈 **Market Analysis** - Analyze property trends in Addis Ababa - 🎓 **Data Science Education** - Perfect for teaching and learning - 🧪 **Model Benchmarking** - Test algorithms on Ethiopian housing data --- ## 🎯 Why Synthetic Data? | Challenge | Solution | |-----------|--------------| | ❌ **Jiji.com can't be scraped** (anti-bot protection) | ✅ Manual extraction of real distribution patterns | | ❌ **Limited real data availability** | ✅ Scalable synthetic generation (any sample size) | | ❌ **Privacy & ethical concerns** | ✅ No real property information exposed | | ❌ **Data imbalance issues** | ✅ Controlled, balanced distributions | | ❌ **Costly data collection** | ✅ Free, instant dataset generation | --- 📚 Documentation - **Data Dictionary** - Complete feature descriptions with examples - **API Reference** - Function documentation - **Contributing Guide** - How to contribute 🤝 Contribu …