LOOH (Leave One Out House)

Inspiration

Empowering Users with Accurate and Dynamic Housing Price Predictions

What it does

LOOH (Leave One Out House) predicts housing prices based on user inputs.

How we built it

We utilized Flask (Python) for the backend and React for the frontend. Additionally, we employed RidgeCV from the scikit-learn library for the linear regression model.

Challenges we ran into

We faced challenges in preprocessing the Kaggle dataset and determining the optimal lambda value for the best model.

Accomplishments that we're proud of

We achieved a high accuracy rate of approximately 95%.

What we learned

Through this project, we gained deeper insights into machine learning models, building Flask backends, and developing React frontends.

What's next for LOOH (Leave One Out House)

In the future, we plan to integrate real-time data by utilizing APIs, enhancing the application's value. Additionally, implementing error range indicators on top of the predicted prices will provide users with a better understanding of the current housing price prediction results. These enhancements will further improve the usability and accuracy of the application, offering users a more comprehensive experience.

Built With

• flask
• nextjs
• numpy
• python
• react
• scikit-learn
• tailwindcss
• typescript