Canada Home Price Prediction | Full ML + Flask Deployment | Python Portfolio Project

In this video, I build a complete end-to-end machine learning project that predicts home prices across Canadian cities — and deploy it as a live web app using Flask. This is exactly the kind of full-stack data science project that stands out in interviews and on your GitHub.
What you'll learn:
✅ Data cleaning and feature engineering on real Canadian housing data
✅ Handling missing values, outliers, and one-hot encoding at scale
✅ Head-to-head model comparison — Linear Regression vs Decision Tree vs XGBoost
✅ Why XGBoost outperforms simpler models on structured housing data
✅ Building a prediction function for real cities — Toronto, Vancouver, Barrie
✅ Deploying your ML model as a REST API with Flask
✅ Connecting a frontend UI to a live Python backend
Tech Stack: Python · pandas · scikit-learn · XGBoost · Flask · NumPy · Matplotlib · seaborn · One-Hot Encoding
🏆 Best Model: XGBoost — highest accuracy across Canadian city predictions

📂 Full source code on GitHub: https://github.com/Sajalagarwal-ca/forecast-home-prices-in-canada/
📊 Dataset: Canadian housing dataset (included in repo)

🔔 Found this useful? LIKE, COMMENT, and SUBSCRIBE — I drop a new Python portfolio project every single week!
Got questions about the Flask deployment or the XGBoost model? Drop them in the comments — I reply to every one!

Видео Canada Home Price Prediction | Full ML + Flask Deployment | Python Portfolio Project канала Sajal Agarwal