Conceptclass imbalance / 类别不平衡
Label Imbalance
Label imbalance is a phenomenon in machine learning in which the number of samples across classes differs greatly, causing metrics such as accuracy to be misleading; evaluation should instead use metrics such as F1, precision, and recall.
Timeline (last 90 days)
Oct 17
Under label imbalance, accuracy is highly misleading: a model that always predicts the majority class can score very high on accuracy while missing every positive example.
Unverified50%