The key to better Feature Engineering for Linear Regression and Machine Learning

• Explore linear relationships between your outcome variable and predictors
• Identify non-linear relationships between your outcome variable and predictors
• Identify collinearity between your predictors

There is much discussion and debate between model selection.

Linear Regression vs Random Forests vs Bagging vs Boosting.

In reality, Garbage In = Garbage Out, so it all starts with identifying the proper variables to include in any analysis, and this tool is built to do just that.

With this tool you can choose from all the variables to compare, and include a regression model of your choosing (LM, Loess, GLM, GAM). And interactivity let’s you identify outliers.

• Introduction to Statistical Learning r datasets (ISLR).