Fractal Interview Questions | Unbalanced Binary Classification
Question
How to deal with unbalanced binary classification? State some common steps for the same.
in progress
0
Interview Question
4 years
1 Answer
610 views
Great Grand Master 0
Answer ( 1 )
There are several techniques to handle unbalanced binary classifier dataset:
We can use random undersampling where the number of instance of majority class is deleted.
We can also use random oversampling where the number of instance of minority class is duplicated
We can use SMOTE ( Synthetic Minority Oversampling Technique) to add instance of minority class. SMOTE uses nearest neighbours of the minority class to create synthetic data.