Demo on synthetic data (Kaggle datasets named on each report). No real client data.

WoWyrdConfidential

WoWyrd · Rule review

Rule review: extended management report

Prepared for Demo client (aml-hi, synthetic)

Client: Demo client (aml-hi, synthetic). Data: 2022-09-01 to 2022-09-18 (daily periods). Cut-off: 2022-09-18 (set for this run). Generated: 2026-11-20 10:02 UTC.

Internal report. Do not share it outside your firm.

Internal report. Do not share it outside your firm.

This is the extended management report. The short management report is management.html; the technical report is technical.html.

Headline numbers

58,331
Transactions reviewed
Transactions file, 2022-09-01 to 2022-09-18
53,483
Alerts
Rule-hit log, 2022-09-01 to 2022-09-18
967
Confirmed fraud
Labels file, known by 2022-09-18
50,302
False alarms
Rule-hit log and labels, mature hits, 2022-09-01 to 2022-09-18
249,889.60 USD
False-alarm cost (estimate)
Your unit costs, 2022-09-01 to 2022-09-18
96.0%
Share of fraud with a rule hit
Labels and rule-hit log, 2022-09-01 to 2022-09-18

Value in your own costs

In 2022-09-01 to 2022-09-18, false alarms took 5,030.2 analyst hours and cost 249,889.60 USD. Source: your unit costs and the rule-hit log.

5 of the top actions touch different rules. Together they remove 7,896 alerts and save 37,704.00 USD over the same period. They lose 41 caught fraud cases. This is a backtest on past data, not a forecast.

Charts

Alerts and confirmed fraud per period18 periods from 2022-09-01 to 2022-09-18. Alerts total 53,483; confirmed fraud total 967.Alerts8,34002022-09-01: 7,339 alerts2022-09-02: 8,340 alerts2022-09-03: 2,312 alerts2022-09-04: 2,383 alerts2022-09-05: 5,879 alerts2022-09-06: 5,775 alerts2022-09-07: 5,731 alerts2022-09-08: 5,790 alerts2022-09-09: 7,250 alerts2022-09-10: 2,520 alerts2022-09-11: 60 alerts2022-09-12: 45 alerts2022-09-13: 29 alerts2022-09-14: 18 alerts2022-09-15: 3 alerts2022-09-16: 3 alerts2022-09-17: 5 alerts2022-09-18: 1 alerts8,340Confirmed fraud12202022-09-01: 64 confirmed fraud2022-09-02: 83 confirmed fraud2022-09-03: 66 confirmed fraud2022-09-04: 80 confirmed fraud2022-09-05: 112 confirmed fraud2022-09-06: 114 confirmed fraud2022-09-07: 97 confirmed fraud2022-09-08: 122 confirmed fraud2022-09-09: 115 confirmed fraud2022-09-10: 98 confirmed fraud2022-09-11: 16 confirmed fraud2022-09-12: 0 confirmed fraud2022-09-13: 0 confirmed fraud2022-09-14: 0 confirmed fraud2022-09-15: 0 confirmed fraud2022-09-16: 0 confirmed fraud2022-09-17: 0 confirmed fraud2022-09-18: 0 confirmed fraud1222022-09-012022-09-032022-09-052022-09-072022-09-092022-09-112022-09-132022-09-152022-09-17
Alerts (bars) and confirmed fraud (dashed line) per period. Two scales: fraud is far smaller than alerts. Source: rule-hit log and labels, 2022-09-01 to 2022-09-18.
False-alarm cost by rule, top 8Money sent to 5+ different recipients within 5 days (fan-out) (Rule ID: tp_u21_fan_out_5_benef_5d): 95,904.24 USD; Transfer above 500 USD (Rule ID: tp_u21_transfer_over_500): 77,428.24 USD; Many small payments in, then sent out within a day (Rule ID: tp_ffiec_small_in_rapid_out_24h): 23,994.16 USD; Money in, then almost all of it sent on within 3 days (layering) (Rule ID: tp_u21_layering_10k_90pct_3d): 23,275.53 USD; Single payment above 9,000 USD (Rule ID: tp_u21_large_txn_9k): 17,737.70 USD; Money from 5+ different senders into one account within 5 days (fan-in) (Rule ID: tp_ffiec_fan_in_5_senders_5d): 4,322.97 USD; 10+ mid-size payments in 5 days, over 20,000 USD in total (Rule ID: tp_u21_stats_10tx_1k3k_5d): 3,991.46 USD; More than 2 wire transfers in 7 days (Rule ID: tp_u21_wire_count_gt2_7d): 1,333.86 USDMoney sent to 5+ different recipients within 5 days (fan-out) (Rule ID: tp_u21_fan_out_5_benef_5d)Money sent to 5+ different recipients within 5 days…Money sent to 5+ different recipients within 5 days (fan-out) (Rule ID: tp_u21_fan_out_5_benef_5d): 95,904.24 USD95,904.24 USDTransfer above 500 USD (Rule ID: tp_u21_transfer_over_500)Transfer above 500 USDTransfer above 500 USD (Rule ID: tp_u21_transfer_over_500): 77,428.24 USD77,428.24 USDMany small payments in, then sent out within a day (Rule ID: tp_ffiec_small_in_rapid_out_24h)Many small payments in, then sent out within a dayMany small payments in, then sent out within a day (Rule ID: tp_ffiec_small_in_rapid_out_24h): 23,994.16 USD23,994.16 USDMoney in, then almost all of it sent on within 3 days (layering) (Rule ID: tp_u21_layering_10k_90pct_3d)Money in, then almost all of it sent on within 3 da…Money in, then almost all of it sent on within 3 days (layering) (Rule ID: tp_u21_layering_10k_90pct_3d): 23,275.53 USD23,275.53 USDSingle payment above 9,000 USD (Rule ID: tp_u21_large_txn_9k)Single payment above 9,000 USDSingle payment above 9,000 USD (Rule ID: tp_u21_large_txn_9k): 17,737.70 USD17,737.70 USDMoney from 5+ different senders into one account within 5 days (fan-in) (Rule ID: tp_ffiec_fan_in_5_senders_5d)Money from 5+ different senders into one account wi…Money from 5+ different senders into one account within 5 days (fan-in) (Rule ID: tp_ffiec_fan_in_5_senders_5d): 4,322.97 USD4,322.97 USD10+ mid-size payments in 5 days, over 20,000 USD in total (Rule ID: tp_u21_stats_10tx_1k3k_5d)10+ mid-size payments in 5 days, over 20,000 USD in…10+ mid-size payments in 5 days, over 20,000 USD in total (Rule ID: tp_u21_stats_10tx_1k3k_5d): 3,991.46 USD3,991.46 USDMore than 2 wire transfers in 7 days (Rule ID: tp_u21_wire_count_gt2_7d)More than 2 wire transfers in 7 daysMore than 2 wire transfers in 7 days (Rule ID: tp_u21_wire_count_gt2_7d): 1,333.86 USD1,333.86 USD
False-alarm cost per rule in USD. An alert hit by several rules shares its cost equally. Source: your unit costs, 2022-09-01 to 2022-09-18.

Top 5 actions

ActionTypeExpected effect (backtest)Confidence
REC-a9097de7 Retire rule Money sent to 5+ different recipients within 5 days (fan-out): 0.5% of its 39,145 alerts with a known outcome were fraud
tp_u21_fan_out_5_benef_5d: Finds one sender spreading money to many receivers in a short time.
Retire the rule7,624 fewer alerts, 40 caught fraud cases lost, 36,403.20 USD saved (estimate)medium
REC-0e97fd0f Retire rule More than 2 wire transfers in 7 days: 0.0% of its 528 alerts with a known outcome were fraud
tp_u21_wire_count_gt2_7d: Finds a sender who uses wire transfers unusually often.
Retire the rule132 fewer alerts, 0 caught fraud cases lost, 633.60 USD saved (estimate)high
REC-8623ab86 Retire rule 20+ small payments in 5 days, over 20,000 USD in total: 0.6% of its 324 alerts with a known outcome were fraud
tp_u21_stats_20tx_0_1k_5d: Finds many small payments that together move a large sum.
Retire the rule29 fewer alerts, 0 caught fraud cases lost, 139.20 USD saved (estimate)high
REC-5f92ad0d Retire rule Money in, then almost all of it sent on within 3 days (layering): 0.9% of its 13,477 alerts with a known outcome were fraud
tp_u21_layering_10k_90pct_3d: Finds an account that receives a large sum and quickly passes nearly all of it to other people.
Retire the rule109 fewer alerts, 1 caught fraud cases lost, 518.40 USD saved (estimate)medium
REC-c96ac8db Retire rule Wire transfers above 4,999 USD in total within 7 days: 0.0% of its 368 alerts with a known outcome were fraud
tp_u21_wire_total_gt4999_7d: Finds a sender who moves a large total by wire in one week.
Retire the rule2 fewer alerts, 0 caught fraud cases lost, 9.60 USD saved (estimate)high

Effects come from a backtest on 2022-09-01 to 2022-09-18. Selective labels: a declined payment has no outcome, so fraud a rule stopped by declining is not in "caught fraud cases lost". The technical report gives the evidence and caveats for each action. A rule name links to its entry in the rule glossary. Each action has a reference (REC-…). Quote this reference in your change record.

Your tools: what each one adds

Demo: the tool names and the tool map are made up. The rules are the demo's own rules.

Each rule belongs to one tool, from your tools.csv. Rules that are not in the map are grouped as "Not assigned". An alert's cost is shared equally among the tools that fired on it, so the tool costs add up to the total false-alarm cost. Catch rate = caught / all mature fraud with a known outcome (948 cases).

ToolRulesAlertsCaughtCatch rateFalse alarmsPrecisionFalse-alarm cost (estimate)Only this tool caught
Transaction monitoring (example)743,79228730.3%41,3420.7%121,748.27 USD50
In-house rules (example)236,68583788.3%33,5952.4%93,887.87 USD508
AML monitoring (example)217,42116617.5%15,2521.1%34,253.47 USD7

Overlap between tools

Caught by ↓, also caught by →Transaction monitoring (example)In-house rules (example)AML monitoring (example)
Transaction monitoring (example)—77.4% (222)18.1% (52)
In-house rules (example)26.5% (222)—17.2% (144)
AML monitoring (example)31.3% (52)86.7% (144)—

Each cell: the share of the row tool's caught fraud that the column tool also caught, with the count. A tool with fewer than 10 caught cases shows "too few to compare".

Fraud types per tool

Fraud typeTransaction monitoring (example)In-house rules (example)AML monitoring (example)
no type given129 (48 only)329 (223 only)65 (7 only)
BIPARTITE8 (0 only)47 (34 only)8 (0 only)
CYCLE10 (0 only)41 (29 only)5 (0 only)
FAN-IN11 (0 only)50 (20 only)21 (0 only)
FAN-OUT54 (2 only)75 (21 only)17 (0 only)
GATHER-SCATTER24 (0 only)81 (40 only)19 (0 only)
RANDOM8 (0 only)40 (32 only)2 (0 only)
SCATTER-GATHER19 (0 only)94 (56 only)22 (0 only)
STACK24 (0 only)80 (53 only)7 (0 only)

Caught fraud cases per fraud type in your labels; in brackets, the cases only this tool caught.

If one tool were off (backtest on past data, not a forecast)

ToolAlerts removedCaught fraud cases lostCost saved (estimate)
Transaction monitoring (example)10,8685051,918.40 USD
In-house rules (example)7,56250833,451.20 USD
AML monitoring (example)58472,764.80 USD

Only the payments where this tool alone fired change. Cost uses the same either/or rule as the rest of the report: analyst time when not declined, friction when declined.

Your tools over time

The technical report compares each tool's precision and catch rate between 2022-09-05 to 2022-09-07 and 2022-09-08 to 2022-09-10, with the counts and the changes larger than our limit. This page shows none of them, so that no small window count can be worked out from this page.

What this data cannot show

  1. A tool whose score or decision is not in your export cannot be measured here. Access to a tool is not use of it: this report measures only what your hit log recorded.
  2. A tool that acts before the hit log is written (for example a decline at authorization) is not visible here.
  3. A declined payment has no outcome, so a tool that declines payments gets less credit than it may deserve.
  4. "Tool off" assumes your other tools would have acted the same. They may not: one tool's decision can change what another tool sees.
  5. A score band is one cut-off. The same tool at another cut-off can catch more or less.
  6. Two windows of three periods show a change, not its cause. A change in the tool's set-up, in your traffic or in your labels can each move the figures. A window counts periods that hold data, not calendar periods: a gap in your export makes a window span more time, and the table per period shows it.

For internal use. Check your vendor contracts before you share tool-level numbers outside your firm.

What changed since the previous report

No previous report was given, so this report is treated as the first one. There is nothing to compare with yet. The next run can compare with this one.

Coverage by fraud type

Fraud types present in your labels

Fraud types present in your labelsSpread, then collect: 97 caught, 1 missed; Layers of accounts: 83 caught, 3 missed; Collect, then spread: 83 caught, 1 missed; One out to many (fan-out): 83 caught, 0 missed; Many into one (fan-in): 52 caught, 2 missed; Two groups paying each other: 47 caught, 2 missed; Money in a circle: 43 caught, 1 missed; Random hops: 40 caught, 1 missed; Type not given: 400 caught, 28 missedSpread, then collectSpread, then collectSpread, then collect: 97 caughtSpread, then collect: 1 missed97 caught, 1 missedLayers of accountsLayers of accountsLayers of accounts: 83 caughtLayers of accounts: 3 missed83 caught, 3 missedCollect, then spreadCollect, then spreadCollect, then spread: 83 caughtCollect, then spread: 1 missed83 caught, 1 missedOne out to many (fan-out)One out to many (fan-out)One out to many (fan-out): 83 caught83 caught, 0 missedMany into one (fan-in)Many into one (fan-in)Many into one (fan-in): 52 caughtMany into one (fan-in): 2 missed52 caught, 2 missedTwo groups paying each otherTwo groups paying each otherTwo groups paying each other: 47 caughtTwo groups paying each other: 2 missed47 caught, 2 missedMoney in a circleMoney in a circleMoney in a circle: 43 caughtMoney in a circle: 1 missed43 caught, 1 missedRandom hopsRandom hopsRandom hops: 40 caughtRandom hops: 1 missed40 caught, 1 missedType not givenType not givenType not given: 400 caughtType not given: 28 missed400 caught, 28 missed
Labelled fraud cases per type. Blue: a rule fired on the payment. Orange: no rule fired. Source: labels file and rule-hit log, labels known by the cut-off.
Fraud typeLabelled casesCaughtMissedWoWyrd
Spread, then collect98971WoWyrd rule available: Money leaves soon after it arrives
Layers of accounts86833WoWyrd rule: planned
Collect, then spread84831WoWyrd rule available: Money leaves soon after it arrives; Many small credits, then one large payout
One out to many (fan-out)83830WoWyrd rule available: One account pays many different payees
Many into one (fan-in)54522WoWyrd rule available: Many senders pay one account; One payee shared by several customers
Two groups paying each other49472WoWyrd rule: planned
Money in a circle44431WoWyrd rule: planned
Random hops41401WoWyrd rule: planned
Type not given42840028WoWyrd rule: planned

Not in this dataset, so it cannot be measured here

Your labels hold no case of these types, so this data cannot show whether your rules catch them. This is not a gap in your rules.

New in our reference set since your last report

Our reference set: version v0.7.0, published 2026-11-18 (built into this collector).

This is the first report with a record of our reference set. The next report lists what is new since this one.

Incoming payments and money-mule signs

Incoming payments not measured: your transactions file has no direction column (for example direction, with values such as in and out).

Requirements changed since the last review

Your rules are mapped to current requirements. We flag when a new requirement affects them. We follow official publications of regulators in Ukraine, the EU, the UK and the US.

Not legal advice. This report maps your rules to requirements, in our own short wording. It is not legal advice. You decide how you comply.

Requirements library read on 2026-11-11. No change file was given for this run, so no changed requirement is listed here.

Requirements still open since the previous report

No previous report was given, so this report is treated as the first one. There is nothing to compare with yet. The next run can compare with this one.

Requirements that showed a gap are followed up only when the two reports compare.

Not legal advice. Your compliance team decides how a requirement applies to you. Public cases show how regulators have treated the same kind of gap; they do not predict an outcome for you.

Regulatory checks by regulator

Not legal advice. This report maps your rules to requirements, in our own short wording. It is not legal advice. You decide how you comply.

Regulatory statuses as of 2026-11-11 (library date). Check them again before you rely on this report.

Grouped by regulator. Our own short wording, not the regulator's text. The technical report gives each finding and its evidence.

Checks per NBU requirements

Rows citing the NBU draft of 17.07.2026 — draft, not in force: its text can change before adoption. Resolutions 51, 54 and 116 are in force. Bill 16013 is a Ukrainian bill, shown here with its status.

Requirement (our wording)ResultSource statusAs ofOfficial source
The acquirer passes payee (merchant) name and category code to the issuer. Check that these fields are filled in your data. Most time-relevant item: the deadline is about 20.11.2026.Not measurable from these filesin force since 20.05.2026; 6 months to comply (about 20.11.2026)2026-11-11bank.gov.ua
Review every rule at least monthly by back-testing it.Gapdraft (NBU draft resolution on control of payment operations, published 2026-07-17; not law)2026-11-11bank.gov.ua
Metric 1: compare how often each rule fired with how many payments were actually stopped.Partly metdraft (NBU draft resolution on control of payment operations, published 2026-07-17; not law)2026-11-11bank.gov.ua
Metric 2: share of fraud value that was prevented, out of all fraud value.Partly metdraft (NBU draft resolution on control of payment operations, published 2026-07-17; not law)2026-11-11bank.gov.ua
Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review.Gapdraft (NBU draft resolution on control of payment operations, published 2026-07-17; not law)2026-11-11bank.gov.ua
Record a review decision for every rule: keep, adjust or cancel.Partly metdraft (NBU draft resolution on control of payment operations, published 2026-07-17; not law)2026-11-11bank.gov.ua
Have evidence ready for a supervisor: documents, rules, risk markers.Partly metdraft (NBU draft resolution on control of payment operations, published 2026-07-17; not law)2026-11-11bank.gov.ua
Show the acquirer's full name before an online payment; receipts show payee, commission, purpose and category code.Not measurable from these filesin force since 20.05.2026; 6 months to comply (about 20.11.2026)2026-11-11bank.gov.ua
Reconcile payment operations every day.Partly metdraft (NBU draft resolution on control of payment operations, published 2026-07-17; not law)2026-11-11bank.gov.ua
Acquiring for natural persons only for allowed categories, with the required data passed to the issuer.Not measurable from these filesin force since 20.05.2026; 6 months to comply (about 20.11.2026)2026-11-11bank.gov.ua
Non-bank providers that acquire payments need an authorisation; the sanctions pause has ended.Not measurable from these filesin force; grace period ended 02.09.20262026-11-11bank.gov.ua
Remote verification of natural persons uses the updated procedure with credit-bureau data.Not measurable from these filesin force since 10.10.2026; 3 months to align internal procedures (about 10.01.2027)2026-11-11bank.gov.ua
Reports to the State Financial Monitoring Service go only through the e-cabinet, with numbered registers.Not measurable from these filesin force since 10.10.2026; 3 months to align internal procedures (about 10.01.2027)2026-11-11bank.gov.ua
Passing cards, account access or payment data to fraudsters becomes a crime. Detect and restrict accounts used as drops.Not measurable from these filesadopted by the Rada 28.10.2026; presidential signature not confirmed2026-11-11itd.rada.gov.ua

Checks per EU requirements

Requirement (our wording)ResultSource statusAs ofOfficial source
When a payee name check fails because of the payee's provider, that provider compensates the payer's provider. Keep evidence of the name check on received transfers.Not measurable from these filesagreed, not adopted (EU Payment Services Regulation; adoption expected by 12.2026)2026-11-11oeil.europarl.europa.eu

Checks per UK requirements

Requirement (our wording)ResultSource statusAs ofOfficial source
A claim may carry an excess of up to 100 GBP, never for vulnerable customers.Not measurable from these filesin force2026-11-11psr.org.uk
Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice.Partly metguidance in force2026-11-11fca.org.uk

Checks per US requirements (FinCEN, NYDFS, FFIEC, Nacha, Federal Reserve)

FinCEN and Nacha items are not checked from your files in this run; the rows below are NYDFS and FFIEC items.

Requirement (our wording)ResultSource statusAs ofOfficial source
Analyse scenarios, rules and thresholds on an ongoing basis.Partly metin force2026-11-11dfs.ny.gov
Test rules before and after they go live.Not measurable from these filesin force2026-11-11dfs.ny.gov
Tune and validate monitoring; justify each threshold.Partly metguidance2026-11-11bsaaml.ffiec.gov

Fraud types in plain words

Each fraud type named in your labels, in one sentence. The word in small grey text is the label as your file gives it.

Collect, then spread GATHER-SCATTER
Money from many accounts is collected in one, then sent on to many others.
Layers of accounts STACK
Money passes through several layers of accounts in a row, so its origin is hard to trace.
Many into one (fan-in) FAN-IN
Many accounts send money into one account, which collects it.
Money in a circle CYCLE
Money passes along a chain of accounts and comes back to the account it left.
One out to many (fan-out) FAN-OUT
One account sends money out to many accounts, so it spreads thin.
Random hops RANDOM
Money hops between accounts along an irregular path with no fixed shape.
Spread, then collect SCATTER-GATHER
Money is split across many accounts, then collected again in one account.
Two groups paying each other BIPARTITE
One group of accounts pays a second group, with many payments crossing between them.
Type not given no type
Fraud labels in your file that do not say which kind of fraud it was.