Do Transaction-Level and Actor-Level AML Queues Agree? An Empirical Evaluation of Granularity Effects on the Elliptic++ Graph

Computer Science > Artificial Intelligence arXiv:2604.23494 (cs) [Submitted on 26 Apr 2026] Title:Do Transaction-Level and Actor-Level AML Queues Agree? An Empirical Evaluation of Granularity Effects on the Elliptic++ Graph Authors:Ankur Malik View a PDF of the paper titled Do Transaction-Level and Actor-Level AML Queues Agree? An Empirical Evaluation of Granularity Effects on the Elliptic++ Graph, by Ankur Malik View PDF HTML (experimental) Abstract:Graph-based anti-money laundering (AML) systems on blockchain networks can score suspicious activity at two granularity levels -- transactions or actor addresses -- yet compliance action is conducted per actor. This paper contributes an evaluation methodology for measuring how scoring granularity affects investigation queue composition under fixed review budgets. We formalize the evaluation through a projection framework mapping transaction-level scores to the actor-level action unit via four aggregation operators, and introduce budgeted investigation metrics -- yield@budget, burden decomposition, and case fragmentation. Using the public Elliptic++ Bitcoin dataset (203,769 transactions; 822,942 address occurrences), we train independent random forest classifiers at each level under a causal temporal protocol and compare review queues through Jaccard overlap, burden decomposition, and feature-matching ablations. At one-percent budget, temporal evaluation yields mean Jaccard of 0.374 (SD 0.171); static pooled evaluation yields 0.087 (95% CI [0.079, 0.094]). An enriched address model receiving all 237 features produces even lower overlap (Jaccard=0.051), with 4.3% illicit per 100 reviews versus 30.2% for the transaction-projected queue. Address-level detection value is temporally concentrated: two timesteps exceed 91% illicit per 100 reviews while the static burden is only 3.4%. A fixed hybrid policy underperforms the best single-level queue by 5.05pp (CI [-10.2pp, -0.9pp]). These findings establish that scoring granularity is a consequential design variable for AML investigation systems -- same data, same budget, different queues, different addresses investigated. Comments: 20 pages, 9 tables, 4 appendices Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) ACM classes: I.2.6; H.4.2 Cite as: arXiv:2604.23494 [cs.AI] (or arXiv:2604.23494v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2604.23494 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Ankur Malik [view email] [v1] Sun, 26 Apr 2026 01:54:11 UTC (23 KB) Full-text links: Access Paper: View a PDF of the paper titled Do Transaction-Level and Actor-Level AML Queues Agree? An Empirical Evaluation of Granularity Effects on the Elliptic++ Graph, by Ankur MalikView PDFHTML (experimental)TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-04 Change to browse by: cs cs.LG References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is…

This excerpt is published under fair use for community discussion. Read the full article at arXiv.org.