House price predction

-Built an XGBoost regression model to predict house prices using key numerical and categorical property features.

-Performed comprehensive data preprocessing, including handling missing values, encoding categorical variables with LabelEncoder, and splitting data for model training and validation.

-Applied hyperparameter tuning with GridSearchCV to optimize the model’s performance.

-Evaluated results using Mean Squared Error (MSE) and R² Score, achieving strong predictive accuracy and generalization.

-Deployed an interactive Streamlit web app that allows users to input property details and receive instant price predictions.

-Ensured model portability and reproducibility by exporting the trained model using joblib and managing dependencies via requirements.txt.