chighislian/real-estate-price-prediction-system

A machine learning web application that predicts house prices in Nigeria based on property features like location and characteristics. Built with Python, Django and scikit-learn, it includes a trained regression model and a simple web interface for real-time price predictions. # 🏠 House Price Prediction (Nigeria) ## Project Overview This project focuses on building a machine learning system that predicts house prices across different states in Nigeria. The goal is to use historical housing data to estimate property prices based on selected housing features. The model is designed to help buyers, sellers, and real estate stakeholders understand housing price trends and make data-driven decisions. ## 📊 Dataset The dataset used for this project contains housing information across Nigeria. It includes property details and pricing information used to train and evaluate the prediction model. Dataset File: • nigeria_houses_data.csv The dataset contains housing attributes such as: • Location • Property features • Housing characteristics • Price information ## 🧠 Machine Learning Approach This project applies supervised machine learning techniques to predict house prices based on input housing features. Workflow 1. Data Collection 2. Data Cleaning and Preprocessing 3. Feature Selection 4. Model Training 5. Model Evaluation 6. Prediction Interface Development ## 🛠️Technologies Used • Python • Machine Learning Libraries (Scikit-learn, Pandas, NumPy) • Web Technologies • HTML • CSS • JavaScript ## 📁 Project documentation ```` HousePricePrediction/ │ ├── HousePricePrediction/ # Project Core │ ├── settings.py # Project configuration & app registration │ ├── urls.py # Main routing and endpoint definitions │ └── wsgi.py # Gateway interface for web deployment │ ├── static/ # Assets Folder │ ├── css/ # Custom styling (Bootstrap/Tailwind) │ ├── js/ # Frontend logic and form handling │ └── img/ # Project screenshots and icons │ ├── templates/ # HTML Layouts │ ├── index.html # Main prediction dashboard │ └── result.html …