0
$\begingroup$

I am working with more than one dataset. So, I have to test my Random Forest Model over 4 datasets. The parameter grid I am taking for dataset D1 is not producing good results for dataset D2 and so on. I have tried multiple range of parameters but none is working for all datasets. Please suggest if their is any empirical/ analytical way by which I can set a common parameter grid for all datasets.

$\endgroup$
0
$\begingroup$

Why are you keeping these data sets separate? If you want to keep them separate, then you could use these data sets as your folds for k-fold cross validation. Then choose the parameter set which leads to the best average performance.

$\endgroup$
1
  • $\begingroup$ All these datasets have different dimensions, i.e. no two datasets have common features. So I can't club them together. $\endgroup$ – Swarnima Jun 10 at 4:51

Your Answer

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

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