Is it beneficial to perform dimensionality reduction before fitting an SVM? Why or why not?

Data Science Interview Questions › Category: Data Science › Is it beneficial to perform dimensionality reduction before fitting an SVM? Why or why not?
0 Vote Up Vote Down
MockInterview Staff asked 6 years ago
1 Answers
0 Vote Up Vote Down
MockInterview Staff answered 6 years ago
  • When the number of features is large comparing to the number of observations (e.g. document-term matrix)
  • SVM will perform better in this reduced space

Source

Your Answer

13 + 0 =