abdoahmed77/Egypt-Hotel-Price-Analysis-Prediction-booking.com-

End-to-end data science project: Selenium web scraper collecting 1,040+ hotel listings from Booking.com across 17 Egyptian cities, followed by EDA, feature engineering, and 7 regression models (Lasso, XGBoost, Random Forest) to predict nightly prices in EGP. # 🏨 Egypt Hotel Price Analysis & Prediction **An end-to-end data science project — from scraping live hotel data to training machine learning regressors that predict nightly prices across Egypt.** 📊 Dataset • 🔬 EDA • 🤖 Models • 📈 Results • 🚀 Usage --- ## 📌 Project Overview This project builds a complete data science pipeline around the Egyptian hotel market. Live hotel listings were scraped from **Booking.com** across **17 Egyptian cities**, covering everything from five-star Hurghada resorts to budget hostels in Upper Egypt. The collected data was then cleaned, explored through rich visualisations, and used to train **seven regression models** that predict the nightly room price in Egyptian Pounds (EGP). **Objectives:** - Design and execute a production-grade Selenium web scraper capable of harvesting hotel attributes at scale from Booking.com. - Conduct thorough exploratory data analysis to uncover pricing dynamics across cities, property types, amenities, and booking policies. - Engineer meaningful features from raw scraped text (amenity flags, distance normalisation, meal-plan encoding). - Train and compare a diverse set of regression algorithms, evaluate them rigorously, and identify the best performer. - Persist the cleaned dataset to a **SQLite** database and demonstrate analytical SQL queries. --- ## 📂 Dataset Information | Attribute | Value | |---|---| | 📋 **Total Records** | 1,040 hotel listings | | 🗂️ **Total Features** | 19 raw columns (expanded to 303 after feature engineering) | | 🌍 **Data Source** | Booking.com | | 🤖 **Collection Method** | Automated Selenium web scraper (`undetected-chromedriver`) | | 📅 **Scraped Date** | May 9, 2026 (check-in: June 1 → June 2, 2026) | | 💱 **Currency** | Egyptian Pound (EGP) | | 🗺️ **Geographic Coverage** | 17 cities across Egypt | | 🏙️ **Cities Covered** | Cairo, Alexandria, Hurghada, Sharm El Sheikh, Luxor, Aswan, El Gouna, Dahab, Marsa Alam, Siwa Oasis, Ain Sokhna, El Alamein, Marsa Matruh, Fa …