Mini project · Semester 5 · Computer Science and Engineering

House Price Prediction Using Machine Learning

Python, Flask, Machine Learning, Scikit-learn, Pandas, NumPy, Random Forest, Gradient Boosting, Ridge Regression, Stacking Ensemble, SQLite, HTML, CSS, Bootstrap, Joblib

View project files ↓Read about this project
10 visitors0 file downloads4 screenshots
THE IDEA

About this project

House Price Prediction Using Machine Learning is an advanced web-based ML application that estimates property prices based on location and property characteristics. Users can enter details such as city, locality, area in square feet, BHK, bathrooms, property age, parking, floor, furnishing status and distance from the city center. The system processes these inputs using an advanced Stacking Ensemble model combining Random Forest, Gradient Boosting and Ridge Regression to generate an estimated property price. The application also maintains prediction history and provides an analytics dashboard with model performance information.

What this project does

  • Advanced house price prediction, Stacking Ensemble Machine Learning model, Random Forest and Gradient Boosting integration, automated data preprocessing, 11 property/location input parameters, estimated property value, indicative price range, predicted price per square foot, prediction history, SQLite database, analytics dashboard, R²/MAE/RMSE model metrics, JSON prediction API, responsive web interface.

What you need

Python 3.10 or above, pip, Flask, Pandas, NumPy, Scikit-learn, Joblib, SQLite and a modern web browser. VS Code is recommended. Minimum 4 GB RAM; 8 GB recommended for smoother model training.

How to run this project

1. Extract the downloaded ZIP file. 2. Open the extracted project folder in VS Code. 3. Open Terminal. 4. Create virtual environment: python -m venv venv 5. Activate virtual environment: venv\Scripts\activate 6. Install required packages: pip install -r requirements.txt 7. Train the Machine Learning model: python train_model.py 8. After model training is completed, start the Flask application: python app.py 9. Open your browser and visit: http://127.0.0.1:5000/ Important: Run python train_model.py at least once before starting predictions.

Learn, build and make it yours

Read the code, try the features and change the project to match your idea. Make sure you understand how it works before using it for your coursework.

DOWNLOAD & START BUILDING

Download project files

Choose the files you need. Each file shows its price, or is marked free.

Paid downloads stay available in your account when you return to this page. Free resources are supported by ads.