Baby steps but We'll get there
I recently built a Boston House Price Prediction app using Linear Regression, Streamlit, and Render. It was a great learning experience, and I’m happy with how it turned out.
I started by exploring the Boston Housing dataset, cleaning it up, and normalizing the features with StandardScaler. After splitting the data into training and test sets, I trained a Linear Regression model using scikit-learn and evaluated its performance with metrics like R² score. Once the model was ready, I saved it along with the scaler using joblib.
For the frontend, I used Streamlit to create a simple, interactive interface where users can adjust input values—like crime rate, number of rooms, and accessibility—and see the predicted price update instantly.
Instead of using Streamlit’s default sharing, I deployed the app on Render for more flexibility. I set up the project with all the necessary files—app.py, model.pkl, requirements.txt, and a render.yaml config—and connected it to GitHub for seamless deployment.
This project helped me bridge the gap between machine learning theory and real-world application. If you're interested in the code or deployment process, I’d be happy to share more details!
use the link below to view the live project
https://boston-house-price-prediction-2csd.onrender.com/
live model
Top comments (0)