House Price Prediction

Multicollinearity can be a big issue in regression analysis as it can inflate the variance of the regression coefficients making them unstable and difficult to interpret. The most complicated task in this project is dealing with the multicollinearity in the selected Housing dataset.

Dropping highly correlated features reduced the multicollinearity, but the improvement in the model's performance was marginal.

Using Lasso (Least Absolute Shrinkage and Selection Operator) Regression is a type of linear regression that includes a regularization parameter. It not only helps with multicollinearity but also performs feature selection by shrinking the coefficients of less important features to exactly 0. This method showed a slight improvement in the model's performance on the test data.

However, even after these steps, the changes in the model's performance were quite small. This suggests that more investigation and tuning might be necessary to further improve the model's performance and handle the multicollinearity in the data. A comprehensive approach could involve gathering more data.