There is a class-imbalanced labeled dataset with 100'000 samples. 90'000 is "0" and 10'000 is "1". There is a model that predicts the labels. It was runned on the class-balanced (10'000 of "0" and 10'000 of "1") test part obtained from initial dataset. Precision/recall was 0.9/0.9 for the test pa...