Multicollinearity

Course Q&A Machine Learning Specialization Supervised ML: Regression and Classification
1

Hello,

I saw in the lectures that parameters such as x1 were used multiple times in a logistic regression equation, for example x1, x1x2, x1^2. Doesn’t this create multicollinearity?

Thanks.

2

The key is that new features must not be linearly related. Non-linear processes (like quadratic terms) create additional complexity.