Which two techniques should you use to avoid overfitting a classification model to a data set?

Question

Options

• AInclude a small number "noise" features that are not through to be correlated with the dependent
• BReplicate features that are through to be significant predicators of the dependent variable multiple
• CSeparate your input data into a training set that is used for fitting and a test set that is used
• DInclude a regularization term in the model's objective function to control how precisely the model
• EPreprocess the data to exclude a typical observation from the model input

• A
  80% (28)
• B
  11% (4)
• C
  3% (1)
• D
  6% (2)

No community discussion yet for this question.