My data has many features out of which two features have one-to-many relation something like state and country. Now I want to do feature selection to identify key independent features for given dependent feature. I use random tree forest feature importance. While its reasonabally good and gave more Weightage to state (40%), it also gave 10% weightage to Country. Knowing the data I expect it to consider Country as redundant as State is more granular. What is the best way to identify such redundancy (Country in this case) while doing feature selection on data domain one is not so familiar with.


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.