In the datascience packages, normally feature selection is done from the features of the provided datasets.

Which approach is better?
a) feature selection by data scientist manually analysing and then searching for datasources with the features (or)
a) identifying datasources and then selecting features from them

  • 1
    $\begingroup$ Its both, isn't it? You have some dataset, you select/engineer some features from that. Later you realize you need more features, so you go looking for datasets that have those features. Don't know if this sufficient for an answer $\endgroup$ – Paresh May 9 at 6:24

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.