OpenChainGraph Suite · ART-10 · AMLA Transaction-Typology Risk Scorer
Deadline: EU AMLR July 2027

AMLA Transaction-Typology Risk Scorer

Paste or generate a synthetic transaction graph and score it against six AML typology detectors: structuring (sub-threshold splitting), layering (rapid re-transfer chains), funnel accounts (many-to-one aggregation), round-tripping (funds returning to origin), high-velocity (burst activity), and FATF Travel Rule gaps (missing originator/beneficiary info on cross-border transfers). Each transaction receives a composite risk score 0–100. Aligned with EU AMLR (full application July 2027) and FATF Recommendation 16.

AP2 Export Chains: PTG-01 · ART-11 GPU Parallel 6 Typology Detectors Zero PII · Synthetic Only
🔒 All scoring runs locally. All transactions must be synthetic. No data leaves your browser. Do not paste real account IDs, names, or transaction identifiers.
Built-in scenarios
Transaction graph — paste or edit JSON
paste or load a scenario
Transaction schema reference
id string — unique TX identifier
from_account string — sender account ID
to_account string — recipient account ID
amount number — in base currency
currency string — e.g. "USD"
timestamp_day integer — day number (1–365)
cross_border boolean — crosses jurisdiction
has_originator_info boolean — FATF originator data present
has_beneficiary_info boolean — FATF beneficiary data present
Transactions
Accounts
Typology sensitivity weights & thresholds
CTR/STR threshold · structuring detector
FATF Rec. 16 · cross-border minimum
Rapid re-transfer window
1.0
1.0
1.0
1.0
1.0
1.2
0 / 0
Risk assessment
Typology detector results
Account risk profiles
Accounts ranked by composite risk score
Transaction risk scores (0)
IDRiskScoreFromToAmountDayCBTypologies Hit
SAR narrative skeleton (highest-risk accounts)

Auto-generated Suspicious Activity Report narrative template for the top-risk accounts. Replace bracketed placeholders with real investigation findings before submission. This is a structural aid, not a complete SAR.

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.

Run the AINumbers MCP tool `score_aml_typologies`. Task: Score a synthetic transaction graph against six AML typology detectors.
Call it with arguments: {"policy_parameters":{}}
Verify before trusting: this node computes in your browser, so the MCP endpoint returns no execution_hash. Run the tool in the page, export the Policy Mandate artifact it produces, and call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with that artifact.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-10-amla-transaction-typology-risk-scorer.html#p=v1.H4sIAAAAAAAA_wECAP3_e31Dv6ajAgAAAA