What Does Identity Access Buy? Pricing the Surveillance Increments in CBDC Transaction Monitoring

Abstract

Proposals for retail central bank digital currency increasingly accept that anti-money-laundering obligations require identity-linked transaction monitoring. The cost of that requirement has not been measured. This paper builds a tiered ablation harness in which four nested evidence tiers - structure only on unlinked pseudonyms, plus pseudonymous linkage, plus identity attributes, plus watchlist access - are scored on identical data with entity-disjoint folds and entity-clustered bootstrap intervals. A pre-specified degeneracy audit fails the run if any single feature separates the classes above entity-level AUC 0.95; this rejects the wallet-count artefact that drove an earlier version of this work. Equivalence is tested by TOST rather than inferred from a null. On synthetic data the answer is detector-dependent: for a gradient-boosted model, pseudonymous linkage carries the increment and full identity access is statistically equivalent to linkage alone; for a logistic model, identity access is decisively superior on average precision. The marginal value of identity access is therefore model- and metric-dependent rather than a fixed property of the data.