This project is an AI-driven real estate analytics system that predicts property prices using historical housing data and provides structured buying or investment recommendations.
It combines machine learning for price prediction with an agent-based advisory module to assist users in making informed real estate decisions.
- Predict property prices or price ranges
- Identify key price-driving factors
- Provide investment/buying insights
- Build an interactive user interface
- Extend into an agentic AI advisory assistant
- Kaggle Housing Prices Dataset
- Dataful Real Estate Dataset
Features include location, size, rooms, age, and amenities.
- Languages: Python
- Libraries: pandas, NumPy, scikit-learn
- Frontend: Streamlit
- AI/ML: LangGraph / LangChain
- Vector DB: FAISS / ChromaDB (optional)
- Property data upload
- Price prediction
- Model performance metrics
- Advisory report generation
- Market insight summaries
data/: Contains raw and processed datasets.notebooks/: Jupyter notebooks for data exploration and model training.src/: Source code for the application.requirements.txt: Python dependencies.
- Python 3.8+
- Jupyter Notebook / Lab
-
Clone the repository
git clone https://github.com/Nandann018-ux/Valdyr.git cd Valdyr -
Create a Virtual Environment
python3 -m venv venv source venv/bin/activate -
Install Dependencies
pip install -r requirements.txt
1. Create Environment Variables
Create a .env file in the root directory to store your API keys:
GROQ_API_KEY=your_groq_key_here2. Run the Web Application Launch the Streamlit dashboard to predict prices and generate AI advisory reports:
streamlit run app/streamlit_app.py3. Run Jupyter Lab (Optional Data Exploration)
jupyter labNavigate to notebooks/data_exploration.ipynb to explore the dataset and models.