[lab-random-forests] Karolin Diede

[KaroD123]

No description provided.

[ArabellaCM]

Hey Karo! I'm looking at your Random Forest/Smote Lab.

Nice work in applying the SMOTE algorithm

One thing to remember about upsampling is when you apply the classifier to real data you won't be able to upsample it since you don't know the target yet. Ideally you should only upsample after you've already done the train/test split.

I also think it's always useful to look at a confusion matrix when doing a classification problem so you can see how well your model is actually operating.

Otherwise very nice and let me know if you have any more questions about these topics. They are very likely to come up in real life scenarios.