Independent model validation — the process, the required evidence, and the specific tests that catch problems GLM diagnostics miss. Designed around the expectations of PRA SS1/23 and internal MRM frameworks. 5 articles.
C. Evans Hedges (Lemonade, December 2025) derives the first closed-form formula connecting model discrimination to expected loss ratio. LRE translates a correlation improvement ...
insurance-cv v0.3.0 adds SupportPointSplit (distributional train-test splitting via energy distance minimisation) and ChatterjeeSelector (nonlinear feature screening using Chatt...
Conformal prediction gives valid marginal coverage but says nothing about conditional coverage — your intervals can fail for young drivers or flood-zone properties while the por...
D-calibration and ICI are mathematically invalid for competing-risks models. If F_k(inf|x) < 1 — which is always true for lapse, claim, and MTA competing causes — the probabilit...
A 5pp Gini improvement means nothing to a CFO. The Loss Ratio Error framework from arXiv:2512.03242 converts model correlation into expected loss ratio — and from there into pou...