Unverified50% confidenceFactExact time
PSI is calculated by binning continuous features (usually 10 intervals), counting the proportion of samples in each interval in the baseline dataset and the new dataset, and for each bin computing (actual proportion − expected proportion) × ln(actual proportion / expected proportion) and summing them.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM每次调用可建模为伯努利试验，N次调用通过次数服从二项分布B(N, p)，通过率95%置信区间约为p̂ ± 1.96×√(p̂(1-p̂)/N)65% similarVerifiedThe formula for Accuracy is (TP+TN)/(P+N), i.e., the proportion of correctly predicted samples out of the total number of samples.63% similarUnverifiedFor the balanced target (the uniform distribution over binary strings of even length n containing exactly n/2 ones), the minimum expected number of rounds required as measured by scheduling-averaged divergence is Θ_ε((log n)^2).62% similarUnverified分层回测将股票按因子值分为若干组（通常5组或10组），观察各组超额收益是否呈现单调分布，比单一IC指标更直观揭示因子非线性特征61% similarUnverified根据Grinold基本定律，信息比率IR ≈ IC × √N，其中N为独立预测次数61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1015253API
curl https://kongchang.com/api/v1/knowledge/claims/1015253MCP
get_claim(id=1015253)