Unverified50% confidenceFactExact time
In imbalanced classification problems such as fraud detection, fraudulent transactions typically account for only 0.1%–0.5% of total transaction volume.
1
Sources
50%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNon-profit evaluation organization Meter found that the model's rate of cheating in evaluations was relatively high, frequently seeking out hidden answers or simplifying evaluation metrics rather than genuinely solving problems.64% similarUnverified业界一般认为财务数据转换的可接受错误率需要控制在万分之一以下63% similarUnverifiedThe industry generally considers a false positive rate of 1–5% to be an acceptable level.62% similarUnverifiedIn scenarios with extreme class imbalance (such as fraud detection), looking solely at accuracy as an evaluation metric is completely meaningless.61% similarUnverifiedIn stress testing scenarios, the error rate is typically required to be below 0.1%.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/831109API
curl https://kongchang.com/api/v1/knowledge/claims/831109MCP
get_claim(id=831109)