Unverified50% confidenceFactExact time
Correctness AUROC measures the ability of a model to distinguish "correct prediction" from "incorrect prediction", with a value of 0.5 indicating no discriminative power and 1.0 indicating perfect discrimination; it is a threshold-independent metric.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn machine learning, the equivalence margin can be set based on the practical meaning of the metric, for example, an AUROC difference of no more than 0.01.78% similarVerifiedAUC值域为0.5到1.0，0.5代表随机猜测、1.0代表完美预测，不受样本类别不平衡影响78% similarUnverifiedAUC是衡量二分类模型综合性能的核心指标，0.5代表随机猜测，1.0代表完美分类76% similarUnverifiedCalibration means that when the model outputs 0.9, across a large number of similar samples about 90% are indeed the correct class; an uncalibrated model can have high AUC but its values cannot be used directly as probabilities.75% similarVerifiedAn AUC=1 on the ROC curve indicates a perfect classifier, while AUC=0.5 is equivalent to random guessing.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088400API
curl https://kongchang.com/api/v1/knowledge/claims/1088400MCP
get_claim(id=1088400)