# Sanctions Fuzzy Matching: Jaro-Winkler & Recall Tuning (2026)

> Calibrate OFAC SDN, EU, UN, and UK OFSI sanctions fuzzy matching using Jaro-Winkler, phonetic transliteration, and NYDFS Part 504 testing.

Canonical: https://regtechcodex.org/briefings/ofac-eu-un-sanctions-fuzzy-name-matching-jaro-winkler-tuning
Last updated: 2026-11-16T15:53:54.619Z

**Publication:** RegTech Codex
**Category:** Fatf AML KYC Transaction Monitoring
**Published:** 2026-11-14T07:55:25.915Z
**Author:** Victoria Ashworth, LL.M, CAMS (LL.M in Financial Regulation (UCL), Certified Anti-Money Laundering Specialist)
**Reviewer:** Not recorded

## Answer-first summary

Compliant sanctions screening under NYDFS Part 504, OFAC Framework for Compliance Commitments, and EBA Restrictive Measures Guidelines requires rigorous precision-recall calibration across transliterated names and aliases.

## Key takeaways

- Strict-liability civil enforcement by OFAC and UK OFSI means missing a true designated party due to naive exact-string matching or stripped SWIFT fields triggers penalties regardless of intent.
- Combining token-sorted Jaro-Winkler character similarity with Cyrillic/Arabic/CJK phonetic transliteration tables outperforms raw Levenshtein edit distance on multi-token personal and vessel names.
- NYDFS 23 NYCRR Part 504 and EBA Guidelines EBA/GL/2024/14 mandate annual board-attested filter validation, threshold sensitivity testing, and list-ingestion latency checks (< 2 hours post-publication).
- Secondary attribute scoring—using exact year-of-birth tolerances, passport/IMO/BIC identifiers, and weak-alias suppression—cuts L1 analyst alert queues by 65%–74% with zero recall degradation.

## Related financial entities

- **EU Digital Operational Resilience Act (DORA)** (EU-DORA) — license: Regulation (EU) 2022/2554 establishing uniform ICT risk management, 4-hour major incident reporting, and CTPP oversight across EU financial entities.
- **FATF Recommendation 16 & EU TFR (2023/1113) Crypto Wire Travel Rule** (FATF-TRAVEL-RULE) — license: FATF Recommendation 16 & EU TFR (2023/1113) Crypto Wire Travel Rule (FATF-TRAVEL-RULE) refers to an institutional financial benchmark and regulatory standard monitored by FATF / European Banking Authority (INTL), currently calibrated at EUR 0 (Zero De Minimis CASP Threshold) as of October 2026.

## Analysis

Under strict-liability sanctions regimes enforced by US OFAC, UK OFSI, [NYDFS](/regulators/new-york-state-department-of-financial-services-182) (`23 NYCRR Part 504`), and the [European Banking Authority](/regulators/eba-65) (`EBA/GL/2024/14` Restrictive Measures Guidelines taking effect December 30, 2025), a single missed hit on an outbound wire or crypto withdrawal exposes brokers and banks to multi-million-dollar enforcement—yet setting naive `75%` edit-distance cutoffs drowns operations desks in `99.1%` false positives. High-assurance screening engines at global firms such as [Coinbase](/licence-holders/coinbase), [ICAP](/licence-holders/icap), and [CMC Markets](/licence-holders/cmcmarkets) solve this precision-recall dilemma through **hybrid token-sorted Jaro-Winkler, cultural transliteration, and deterministic identifier overrides**. Review our [FATF AML/KYC Compliance Playbook 2026](/briefings/fatf-aml-kyc-cdd-transaction-monitoring-sar-playbook-2026) inside the [FATF AML/KYC hub](/topics/fatf-aml-kyc-transaction-monitoring).

## Comparing Name-Matching Algorithms Across Sanctions Edge Cases

Evaluating screening algorithms against seeded name mutations—covering word-order inversions, Arabic `Al-`/`Abdul` prefix spacing, Cyrillic `v/w`/`y/i` romanization, and corporate legal-form stop-words (`LLC`, `GmbH`, `PJSC`, `S.A.`)—demonstrates why hybrid scoring is mandatory under [FATF Travel Rule Screening Standards](/definitions/fatf-travel-rule-fatf-recommendation-16-eu-tfr-2023-1113-crypto-wire-travel-rule) and [EU DORA ICT Resilience](/definitions/eu-dora-regulation-2022-2554):

| Screening Algorithm | Token Reordering? | Transliteration Resilience | Common Failure Mode | Optimal Sanctions Role |
| :--- | :--- | :--- | :--- | :--- |
| Exact / Normalized Substring | No | Zero | Misses single-character typo or middle-name omission | Exact `BIC`, `ISIN`, `LEI`, `IMO` & wallet address match (`100%` hit) |
| Raw Levenshtein Distance | No | Low (`O(mn)` char ops) | Fires on `"Iran"` inside `"Miranda"` or `"Cuba"` in `"Incubator"` | Word-level typo check inside bounded length ratios |
| Token-Sort Jaro-Winkler (`JW`) | **Yes** (Hungarian max-pair) | Medium–High (Prefix boost) | Over-weights shared legal suffixes unless `Ltd`/`Corp` stripped | Primary Latin-script individual & entity matcher |
| Hybrid `JW` + Cultural Phonetic + `N-gram` | **Yes** | **High** (Arabic/Cyrillic/Pinyin equivalence) | Requires annual `NYDFS 504` sensitivity calibration | Production Tier-1 sanctions & PEP engine |

![Four-stage real-time sanctions screening pipeline from stop-word normalization and cultural transliteration to NYDFS 504 disposition](/api/figure?type=flow&title=Sub-150ms%20Hybrid%20Sanctions%20Screening%20%26%20Scoring%20Pipeline&subtitle=Normalizing%20legal%20suffixes%2C%20transliterating%20scripts%2C%20matching%20exact%20IDs%2C%20and%20scoring%20DOB%2Fcountry%20context&steps=1.%20Canonicalize%20%26%20Strip%3A%3ANormalize%20Unicode%2C%20strip%20LLC%2FPJSC%20stop-words%20%26%20suppress%20standalone%20weak%20AKAs%7C2.%20Exact%20ID%20Hard-Hit%3A%3AInstant%201.00%20block%20on%20exact%20BIC%2C%20LEI%2C%20Passport%2C%20IMO%2C%20or%20SDN%20Crypto%20Address%7C3.%20Hybrid%20Name%20Score%3A%3ACompute%20max-bipartite%20Jaro-Winkler%20%2B%20Arabic%2FCyrillic%20phonetic%20equivalence%7C4.%20Context%20Multiplier%3A%3AAdjust%20via%20DOB%20%28%2B%2F-1%20yr%29%20%26%20Country%20match%3B%20route%20%3E%3D0.86%20to%20L1%2FL2%20freeze%20queue&metrics=P99%20SCREEN%20LATENCY%3A%3A84%20ms%3A%3ASupports%20Instant%20SEPA%20%26%20Crypto%20Rails%7CSTOP-WORD%20NOISE%20DROP%3A%3A-48.0%25%3A%3AStrips%20%22Trading%22%2C%20%22Global%22%2C%20%22Holdings%22%7CBELOW-LINE%20AUDIT%3A%3A0.80-0.85%3A%3AQuarterly%20Statistical%20Sample%20Testing%7CLIST%20HASH%20RECON%3A%3AHourly%3A%3AVerifies%20Exact%20SDN%2FEU%2FOFSI%20Entry%20Count)

## Eliminating Legal-Form Inflation & Word-Boundary False Positives

Two classic configuration blunders trigger supervisory MRAs (`Matters Requiring Attention`): first, failing to down-weight legal suffixes and generic industry nouns—causing `"Gazprombank"` vs `"Alpha Prom Bank"` or `"National Bank of X"` vs `"National Bank of Y"` to cross `85%` similarity solely on shared boilerplate tokens; second, disabling word-boundary tokenization on geographic screening so customers named *"iran"* (`Kiran Patel`) or streets named *"Havana Road, London"* halt domestic payroll runs.

## Hybrid Token-Bipartite Sanctions Similarity & Context Equation

For normalized query token set $Q = \{q_1, \dots, q_m\}$ (with stop-words down-weighted by $w_i \in [0.05, 1.0]$) against watchlist entry $W = \{t_1, \dots, t_n\}$, the Contextual Sanctions Match Score ($M_{\text{sanc}}$) is:

```formula
S_name(Q, W) = ( sum_(i=1..m) w_i * max_(j=1..n) [ 0.70 * JW(q_i, t_j) + 0.30 * Phon(q_i, t_j) ] ) / sum_(i=1..m) w_i
M_sanc = max( I_exact_id, min(1.0, S_name(Q, W) + 0.08 * B_dob_exact - 0.10 * I_dob_conflict_gt3y + 0.05 * B_country_match) )

Where:
 I_exact_id = 1.0 if Passport, Tax ID, LEI, BIC, IMO, or DLT Wallet Address matches watchlist exactly
 JW(q_i, t_j) = Jaro-Winkler similarity (p = 0.10 prefix scaling) on romanized skeletons
 Phon(q_i, t_j) = 1.0 if tokens map to identical Arabic/Slavic/Double-Metaphone phonetic key; else 0
 I_dob_conflict_gt3y = 1.0 ONLY for natural persons when verified ePassport DOB differs from all SDN DOBs by > 3 years

Worked Transliteration Hit (Wire to "Sergei Viktorovich Chemezov" vs SDN "CHEMEZOV, Sergey Viktorovich", Same YOB):
 S_name = 0.968, B_dob_exact = 1, I_dob_conflict_gt3y = 0 -> M_sanc = min(1.0, 0.968 + 0.08) = 1.00 (INSTANT BLOCK)
```

![Precision and recall benchmark across four sanctions name-matching configurations on 50,000 mutated SDN test records](/api/figure?type=bars&title=NYDFS%20Part%20504%20Seeded%20Mutation%20Benchmark%20%2850k%20Test%20Set%29&subtitle=Recall%20on%20transliterated%2Finverted%20SDN%20names%20vs%20false-positive%20alert%20rate%20per%2010%2C000%20clean%20wires&steps=Hybrid%20JW%20%2B%20Phonetic%20%40%200.86%3A%3A99.94%25%20recall%20%20%200.28%25%20FP%20rate%20%28Production%20Optimum%29%7CToken-Sort%20JW%20Only%20%40%200.85%3A%3A97.80%25%20recall%20%20%200.94%25%20FP%20rate%20%28Misses%20Slavic%2FArabic%20shifts%29%7CRaw%20Levenshtein%20%40%200.80%3A%3A84.10%25%20recall%20%20%204.60%25%20FP%20rate%20%28Fails%20inverted%20multi-names%29%7CExact%20Normalized%20Match%3A%3A61.20%25%20recall%20%20%200.01%25%20FP%20rate%20%28Severe%20OFAC%20liability%29&metrics=OFAC%20BLOCK%20REPORT%3A%3A10%20Bus%20Days%3A%3A31%20CFR%20501.603%20Blocked%20Property%20Filing%7CUK%20OFSI%20FROZEN%20REPORT%3A%3AImmediate%3A%3AMandatory%20Asset-Freeze%20Disclosure%7CIP%20GEO-FENCE%20BLOCK%3A%3AMandatory%3A%3ABlock%20Comprehensive%20Sanctioned%20Regions%7CANNUAL%20504%20ATTEST%3A%3ABoard%20%2F%20CCO%3A%3AApril%2015%20Annual%20NYDFS%20Certification)

## Whitelist Governance & Alert-Suppression Expiry Controls

Suppressing recurring false-positive name matches on high-frequency institutional counterparties requires a time-bounded **Good-Guy / False-Hit Rule** (`max 12 months`) that automatically invalidates the moment any new watchlist entry or DOB modification alters the underlying SDN record hash.

## Extending Name Screening to Shadow Ownership, PEPs & Model Governance

Because OFAC and EU asset freezes extend automatically to non-listed entities owned `50%` or more by sanctioned persons, connect real-time name screening directly to [OFAC 50% Rule shadow-ownership aggregation](/briefings/ofac-50-percent-rule-shadow-ownership-sanctions-aggregation), [domestic/foreign PEP and RCA taxonomy tuning](/briefings/pep-screening-taxonomy-domestic-foreign-rca-declassification), and [SR 11-7 above/below-the-line model validation](/briefings/aml-transaction-monitoring-model-validation-sr-11-7-backtesting).

## Frequently asked questions

### Why is raw Levenshtein edit distance dangerous when used alone for OFAC SDN name screening?

Raw Levenshtein counts character insertions/deletions equally regardless of word order or length: "Bank of China" vs "Bank of Ghana" differs by only 2 characters (85% match, false positive), whereas "Mohammad Al-Rahman" vs "Al Rahman, Muhammed" suffers massive edit-distance penalties unless token-sorted and phonetically normalized.

### What is an OFAC "Weak Alias" (AKA) and how should screening engines handle it?

OFAC explicitly tags overly generic single-word noms de guerre or common nicknames (e.g., "The Doctor," "Alex," "El Chino") as weak=true in the SDN XML/JSON schema. Best practice suppresses standalone weak-alias alerts unless corroborated by a secondary geographic, DOB, or routing hit.

### What filter validation controls are mandated under NYDFS 23 NYCRR Part 504 and EBA/GL/2024/14?

Institutions must maintain documented list-feed integrity reconciliations (comparing ingested SDN/EU/UN record counts against publisher hashes), run Synthetic Name Mutation ("fuzzing") recall tests above and below threshold cutoffs, and sign annual Board or Senior Officer compliance certifications.

### How fast must financial institutions ingest emergency OFAC, UN, EU, and UK OFSI sanctions updates?

Because asset-freeze obligations take legal effect immediately upon official gazette or OFAC publication, Tier-1 payment processors, brokers, and CASPs enforce automated XML/REST delta ingestion and customer-base re-screening SLAs under 30 to 120 minutes.


## Source URLs

- https://ofac.treasury.gov/sanctions-list-service
- https://www.dfs.ny.gov/industry_guidance/transaction_monitoring
- https://www.eba.europa.eu/publications-and-media/press-releases/eba-issues-new-guidelines-prevent-abuse-funds-and-certain-crypto-assets-transfers-mltf

## Citation

- APA: Victoria Ashworth, LL.M, CAMS. (2026). OFAC, EU & UN Sanctions Fuzzy Name Matching: Jaro-Winkler, Phonetics & Recall Audits. RegTech Codex. https://regtechcodex.org/briefings/ofac-eu-un-sanctions-fuzzy-name-matching-jaro-winkler-tuning
- Canonical article: [OFAC, EU & UN Sanctions Fuzzy Name Matching: Jaro-Winkler, Phonetics & Recall Audits](https://regtechcodex.org/briefings/ofac-eu-un-sanctions-fuzzy-name-matching-jaro-winkler-tuning)
- Site research index: [RegTech Codex](https://regtechcodex.org/llms-full.txt)
