Severity modelling specifically: large loss loading, spliced distributions, extreme value theory, dispersion modelling, and the frequency-severity independence assumption that most GLMs get wrong. 6 articles.
Scenario modelling for UK motor bodily injury claims under whiplash reform uncertainty — Taylor separation, severity distributions, and conformal prediction intervals.
Three recent papers on EVT and ML — from generalisation bounds for tail learning to Bayesian nonparametric splicing — and what they actually imply for UK severity models.
EVT for UK motor large loss pricing: censored GPD for open TPBI claims, profile likelihood CIs, excess layer pure premiums. insurance-evt Python library.