+1 vote
in Feature Engineering by
What can be done if you find that most of your features have no predictive power on your target variable?

1 Answer

0 votes
by

If you find that most of your features have no predictive power on your target variable, you can try to remove them and see if that improves your model’s performance. You can also try to create new features that might be more predictive. Finally, you can try to use a different machine learning algorithm that might be better suited to your data.

...