This project focuses on predicting housing prices using regression models based on various property features. By applying thorough data preprocessing, effective feature engineering, and training multiple regression algorithms, we achieved high prediction accuracy. We also implemented a vectorized linear regression model to visualize the Mean Squared Error (MSE) and gain deeper insights into the optimization process.
- Predict house prices using structured data
- Applied multiple regression algorithms for performance comparison
- Cleaned and preprocessed dataset with missing value handling and encoding
- Performed feature engineering to enhance model performance
- Visualized MSE using a custom vectorized implementation of linear regression
- Language: Python
- Libraries: scikit-learn, pandas, NumPy, matplotlib, seaborn
- Algorithms: Linear Regression, Ridge, Lasso, Decision Tree Regressor, Random Forest Regressor
- Visualization: MSE plots for vectorized linear regression