New answers tagged

1 vote

Class imbalance problem in binary classification of ecg and eeg data. I am cross posting it here from stackExchange as per a user suggestion

In your question, you say this: This leads to a class imbalance in the ratio 1:7 (fear:not fear). I am getting false accuracies in the 90% range due to this. To be ...
Karl's user avatar
  • 611
0 votes

SMOTE and multi class oversampling

Not necessarily. There is an option named sampling_strategy which accepts a dictionary that covers the classes and their desired oversampled values. For example, ...
Süleyman Topdemir's user avatar

Top 50 recent answers are included