Could you explain some of the ways dimensionality reduction is carried out in Machine Learning? Does it vary depending on the type of data involved?

Question

Anonymous · Accepted Answer

There are a few dimensionality reduction techniques:
1. PCA: PCA can help reduce the dimensionality while retaining majority of the
information in newly created independent features
2. Feature selection techniques: Several techniques such as Lasso, Tree-Based
models. Forward selection,backward elimination, Correlation plot, VIF, etc. can
help find relevant features for the model and then in turn reduce the
dimensionality

Could you explain some of the ways dimensionality reduction is carried out in Machine Learning? Does it vary depending on the type of data involved?

Practice this question with AI

Go Premium

Practice More Questions

Community Answers

Unlock Community Insights

Everything You Need to Ace DS Interviews