2
$\begingroup$

Could someone please explain how the EasyEnsemble algorithm works? Im using it for a prediction model for imbalanced minority class.

Please don't refer me to this paper, as it makes no sense to me. EasyEnsemble and Feature Selection for Imbalance Data Sets

Im using the algorithm in Pandas, with the UnbalancedDataset library which is on GitHub UnbalancedDataset

I get an array of matrices as O/P, I don't know how to use this in the end, to train with random forests.

Thanks

$\endgroup$
  • $\begingroup$ Where did you learn abt the algorithm? The paper? $\endgroup$ – Dawny33 May 9 '16 at 14:36
  • $\begingroup$ No. Someone else suggested it for my problem. I tried SMOTE but it didn't seem to work. I'll be really grateful if someone could help. As I said it's generating 9 matrices of my attributes and 9 corresponding arrays of output. Thanks $\endgroup$ – TdBm May 9 '16 at 15:50
3
$\begingroup$

The toolbox only manage the sampling so this is slightly different from the algorithm from the paper.

What it does is the following: it creates several subset of data which are balanced. These subsets are created by randomly under-sampling the majority class. That is what you are getting from the toolbox.

To obtain what in the paper, you need to train an AdaBoost classifier for each subset. Thus, what you get is an ensembles of ensembles.

Hope that's help.

| improve this answer | |
$\endgroup$

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.