When building an ensemble model (eg random forest), are there good ways to group observations known to be highly correlated rather than IID?
-
-
@patrickc well should figure that part out first. some descriptive stats? can also reverse the model & see where the results are correlated -
@ihat@patrickc principle component analysis? I recall doing this to remove / group attrs that held correlation (see http://jeffreyiacono.github.io/pml/ )
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.