1
$\begingroup$

I have a binary Classification problem and I have a dataset with lot of categorical variables and many of them have missing information. I proceeded with dropping all the missing values from the dataset and lost many rows of data.

Should I take another level(category) for the missing values and put it in the model. But I am not sure if they all are missing due to similar particular condition. What should be done in these scenarios?

$\endgroup$
1
  • $\begingroup$ You could also look into imputation, search this site! $\endgroup$ Dec 23, 2023 at 6:06

1 Answer 1

2
$\begingroup$

It's perfectly reasonable to add "not available" category. If you have different causes of nonavailability, you can create different categories for that as well. But make sure that that causes influence your target class, otherwise "not available" will be enough.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.