Unverified50% confidenceBenchmarkExact time
After the platform's listing format changed, the AUC for predicting whether a market would reach $1,000 in trading volume dropped from 0.940 in the same period to 0.577 in the cross-period test.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn familiar question forms that had appeared in the training data, the model's AUC for predicting whether a market would reach $1,000 in trading volume still reached 0.778.75% similarUnverifiedThe ranking ability of listing-time features for settlement disputes reached an AUC of 0.78, but the average precision was only 0.012.70% similarVerifiedAccording to common industry standards, AUC > 0.9 is excellent, 0.8–0.9 is good, 0.7–0.8 is fair, 0.5–0.7 is poor, and 0.5 is equivalent to random guessing.65% similarUnverified研究表明将收入从精确值泛化为5个区间可能导致模型AUC下降2-5个百分点64% similarUnverifiedIn the controlled source-migration experiment, DeRef raised AUROC from chance level or below to between 98.40 and 99.59.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084230API
curl https://kongchang.com/api/v1/knowledge/claims/1084230MCP
get_claim(id=1084230)