0

Is there a reason not to standardize all features by default? I realize it may not be necessary for e.g., decision trees but for certain algorithms such as KNN, SVM and K-Means. Would there be any harm just routinely to do this for all of my features?

Also, it seems the consensus that standardization is preferable to normalization? When would this not be a good idea?

Levon
  • 433
  • 7
  • 16
  • 1
    Related [When conducting multiple regression, when should you center your predictor variables & when should you standardize them?](https://stats.stackexchange.com/questions/29781/when-conducting-multiple-regression-when-should-you-center-your-predictor-varia) – user2974951 Feb 22 '21 at 13:10
  • @user2974951 I'm not really just concerned about regression, but other ML algorithms too as I mentioned, some that definitely require standardization, but I'll take a look at the link you provided, thanks. – Levon Feb 22 '21 at 20:14

0 Answers0