WoWyrd · Rule review
Rule review: extended management report
Prepared for Demo client (sepa-2026, synthetic)
Client: Demo client (sepa-2026, synthetic). Data: 2026-10-01 to 2026-11-29 (daily periods). Cut-off: 2026-11-29 (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
Value in your own costs
In 2026-10-01 to 2026-11-29, false alarms took 3,515.5 analyst hours and cost 168,992.00 USD. Source: your unit costs and the rule-hit log.
4 of the top actions touch different rules. Together they remove 683 alerts and save 2,851.20 USD over the same period. They lose 21 caught fraud cases. This is a backtest on past data, not a forecast.
Charts
Top 5 actions
| Action | Type | Expected effect (backtest) | Confidence |
|---|---|---|---|
| REC-f4bb199b Retire rule Many small payments in, then sent out within a day: 2.9% of its 621 alerts with a known outcome were fraud tp_ffiec_small_in_rapid_out_24h: Finds an account that collects several small payments and passes most of the money on at once. | Retire the rule | 1 fewer alerts, 0 caught fraud cases lost, 4.80 USD saved (estimate) | high |
| REC-0bb1e839 Retire rule Money in, then almost all of it sent on within 3 days (layering): 2.1% of its 575 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 rule | 0 fewer alerts, 0 caught fraud cases lost, 0.00 USD saved (estimate) | high |
| REC-1d130941 Retire rule 10+ mid-size payments in 5 days, over 20,000 USD in total: 0.5% of its 1,042 alerts with a known outcome were fraud tp_u21_stats_10tx_1k3k_5d: Finds a burst of many similar mid-size payments that add up to a large total. | Retire the rule | 1 fewer alerts, 0 caught fraud cases lost, 4.80 USD saved (estimate) | high |
| REC-628c02f6 Retire rule Money sent to 5+ different recipients within 5 days (fan-out): 4.0% of its 3,817 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 rule | 681 fewer alerts, 21 caught fraud cases lost, 2,841.60 USD saved (estimate) | medium |
| REC-15831f03 Add a rule for: Gambling winnings arrive with no deposits, then card transfers follow | Add a missing fraud type | No effect estimate. | medium |
Effects come from a backtest on 2026-10-01 to 2026-11-29. 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 (2,063 cases).
| Tool | Rules | Alerts | Caught | Catch rate | False alarms | Precision | False-alarm cost (estimate) | Only this tool caught |
|---|---|---|---|---|---|---|---|---|
| AML monitoring (example) | 3 | 28,122 | 383 | 18.6% | 24,321 | 1.6% | 91,678.13 USD | 102 |
| In-house rules (example) | 2 | 19,455 | 1,316 | 63.8% | 15,743 | 7.7% | 48,552.13 USD | 759 |
| Transaction monitoring (example) | 5 | 13,775 | 487 | 23.6% | 9,936 | 4.7% | 28,761.73 USD | 127 |
Overlap between tools
| Caught by ↓, also caught by → | AML monitoring (example) | In-house rules (example) | Transaction monitoring (example) |
|---|---|---|---|
| AML monitoring (example) | — | 70.8% (271) | 19.3% (74) |
| In-house rules (example) | 20.6% (271) | — | 26.6% (350) |
| Transaction monitoring (example) | 15.2% (74) | 71.9% (350) | — |
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 type | AML monitoring (example) | In-house rules (example) | Transaction monitoring (example) |
|---|---|---|---|
| ato | 103 (31 only) | 434 (263 only) | 177 (62 only) |
| invest | 48 (5 only) | 280 (164 only) | 85 (0 only) |
| invoice | 91 (0 only) | 200 (75 only) | 61 (0 only) |
| purchase | 83 (66 only) | 72 (49 only) | 87 (65 only) |
| safe | 58 (0 only) | 330 (208 only) | 77 (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)
| Tool | Alerts removed | Caught fraud cases lost | Cost saved (estimate) |
|---|---|---|---|
| AML monitoring (example) | 15,577 | 102 | 68,971.20 USD |
| In-house rules (example) | 6,231 | 759 | 23,865.60 USD |
| Transaction monitoring (example) | 3,615 | 127 | 12,158.40 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.
- AML monitoring (example) fired on 70 payments that were declined. Fraud stopped by a decline has no outcome, so this tool's real value may be higher than shown.
- In-house rules (example) fired on 77 payments that were declined. Fraud stopped by a decline has no outcome, so this tool's real value may be higher than shown.
- Transaction monitoring (example) fired on 77 payments that were declined. Fraud stopped by a decline has no outcome, so this tool's real value may be higher than shown.
- Card scheme score (example): no hits in this export. It cannot be measured here.
Your tools over time
The technical report compares each tool's precision and catch rate between 2026-11-16 to 2026-11-18 and 2026-11-19 to 2026-11-21, 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
- 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.
- A tool that acts before the hit log is written (for example a decline at authorization) is not visible here.
- A declined payment has no outcome, so a tool that declines payments gets less credit than it may deserve.
- "Tool off" assumes your other tools would have acted the same. They may not: one tool's decision can change what another tool sees.
- A score band is one cut-off. The same tool at another cut-off can catch more or less.
- 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 type | Labelled cases | Caught | Missed | WoWyrd |
|---|---|---|---|---|
| Account takeover | 698 | 535 | 163 | WoWyrd rule: planned |
| Purchase scam | 539 | 210 | 329 | WoWyrd rule: planned |
| Safe-account scam | 331 | 330 | 1 | WoWyrd rule: planned |
| Investment scam | 299 | 285 | 14 | WoWyrd rule: planned |
| Invoice redirection | 210 | 210 | 0 | WoWyrd rule: planned |
| Money mule | 1 | 0 | 1 | WoWyrd 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.
- One user holds many more accounts or cards than similar users
WoWyrd rule: planned. - One type of operation makes up an unusual share of a user's activity
WoWyrd rule available: One type of operation dominates an account. - Many operations of one type in a short time, incoming or outgoing
WoWyrd rule available: Many requests from one account in an hour, then a payout; A burst of operations of one type. - Balance stays low although large amounts pass through
WoWyrd rule available: Large amounts pass through an account that keeps a low balance. - Large loans are taken and repaid again and again
WoWyrd rule available: Large loans taken and repaid again and again. - Money comes in and leaves fast, little balance stays
WoWyrd rule available: Money leaves soon after it arrives. - Gambling winnings arrive with no deposits, then card transfers follow
WoWyrd rule available: Gambling winnings with no gambling deposits. - Regular transfers to a personal account look like business activity
WoWyrd rule available: A personal account paid by many payers. - A new merchant's volume is far above similar merchants, then the merchant closes
WoWyrd rule available: A merchant with little history suddenly busy. - Merchant account inflows mirror its outflows (transit)
WoWyrd rule available: A business account pays out almost all it receives. - Payment purposes do not fit the merchant's category code
WoWyrd rule available: Payment purpose does not fit the merchant's business; Card payment to a person without category or purpose. - Contacts, device, apps, IMEI, operating system or network address change often
WoWyrd rule available: Payout right after an email or phone change; One session from several network addresses; One account used from many devices. - One device fingerprint is used by unrelated users
WoWyrd rule available: One device used by several customers. - Two operations are too far apart to travel between in the time
WoWyrd rule available: Locations too far apart for the time between them. - One payer sends to far more payees than similar payers
WoWyrd rule available: One account pays many different payees. - Many payers send to one payee, far more than for similar payees
WoWyrd rule available: Many senders pay one account; One payee shared by several customers. - Many different senders pay one account within a short time
WoWyrd rule available: Many senders pay one account. - Most of an incoming amount leaves again within hours
WoWyrd rule available: Money leaves soon after it arrives. - A new account gets large or many credits soon after opening
WoWyrd rule available: A new account receives a large credit; A new account paid by several people. - A dormant account suddenly moves large amounts
WoWyrd rule: planned. - Repeated amounts just under a reporting or limit threshold
WoWyrd rule available: Payments just under a limit; Many small payments from one account add up to a large sum; Many small payments to one payee add up to a large sum. - Repeated round amounts with no business reason
WoWyrd rule available: Several payments in large round amounts. - One account pays many new beneficiaries
WoWyrd rule available: One account pays many different payees. - Outgoing payments per hour above the customer's usual level
WoWyrd rule available: More payments in an hour than the customer usually makes; Many requests from one account in an hour, then a payout. - A large first payment to a payee never paid before
WoWyrd rule available: A large payment to a payee added just before. - Many senders' accounts share one beneficiary
WoWyrd rule available: One payee shared by several customers. - Money goes round in a circle between accounts within days
WoWyrd rule: planned. - An amount far above the customer's own history
WoWyrd rule available: A payment far above the customer's usual amount. - Many small credits, then one large debit
WoWyrd rule available: Many small credits, then one large payout. - Credits from many different banks into one account
WoWyrd rule available: Credits from many different banks into one account. - Transfers to or from high-risk jurisdictions
WoWyrd rule available: A payment to or from a high-risk country. - Cash withdrawn right after a credit arrives
WoWyrd rule available: Cash taken out soon after money arrives. - The payee name does not match and the payment still goes
WoWyrd rule available: Paid although the payee name did not match. - The payment reference mentions investment, crypto or a 'safe account'
WoWyrd rule available: The payment reference uses common scam wording. - An older customer suddenly sends a large amount to a new payee
WoWyrd rule available: An older customer sends a large amount to a new payee. - Activity at hours unusual for the customer
WoWyrd rule available: Activity at an hour unusual for the customer.
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
This part measures incoming payments and three money-mule signs on your own transactions file, with our reference set's limits. FCA CP26/38, a consultation draft, names a focus on outgoing payments only as poor practice and lists money-mule signs. An account with a sign is a lead for your analysts, not a finding about the account holder. The figures give no verdict on your process.
A checklist item asks you to monitor incoming as well as outgoing payments. These figures are data next to your own statement on it; they do not change its result.
Your rule log has 91.3% of incoming credits; a rule fired on 0.0%. For outgoing payments: 100.0% and 71.5%.
| Payments | In your file | In your rule log | A rule fired |
|---|---|---|---|
| Incoming credits | 23 | 21 (91.3%) | 0 (0.0%) |
| Outgoing payments | 59,138 | 59,138 (100.0%) | 42,310 (71.5%) |
| Money-mule sign | Our limits | Accounts | A rule fired during the sign | A rule fired later | Too recent for labels | Mule label | Any fraud label | Your matched rule |
|---|---|---|---|---|---|---|---|---|
| Many senders | more than 2 different senders within 30 days | 5 | 0 | 0 | 0 | fewer than 5 | fewer than 5 | — |
| Money out soon after it came in | at least 80% of the money that came in within 30 minutes sent out in the same time | 1 | 0 | 0 | 0 | not shown: it would reveal a count under 5 | not shown: it would reveal a count under 5 | — |
| New account paid by several people | an account younger than 7 days, paid by at least 2 different senders within 30 days | 1 | 0 | 0 | 0 | not shown: it would reveal a count under 5 | not shown: it would reveal a count under 5 | — |
- Many senders. 5 accounts. A rule fired on 0 during the sign and on 0 later. Mule label: fewer than 5. Any fraud label: fewer than 5.
- Money out soon after it came in. 1 account. A rule fired on 0 during the sign and on 0 later. Mule label: not shown: it would reveal a count under 5. Any fraud label: not shown: it would reveal a count under 5.
- New account paid by several people. 1 account. A rule fired on 0 during the sign and on 0 later. Mule label: not shown: it would reveal a count under 5. Any fraud label: not shown: it would reveal a count under 5.
The limits are our reference set's starting values, not tuned to your data. Reference set v0.7.0, from the reference catalogue that comes with this collector, SHA-256 of the catalogue file 6a5d70c1fdfa3ef833e98cea246df506db35d699ec072159aa0ec0ba2bd04d88.
Each sign is measured on your data with our reference set's limits, over exact time windows. A rule engine that keeps its counts in another way can find other accounts.
Not in this review: the flow of money between accounts (it needs the links between your accounts), and other money-mule signs such as cash withdrawals, dormant accounts, changed login details, new devices and money moved abroad. They need data that this file does not hold.
New accounts and onboarding rating
This part shows fraud and alerts by account age and by your onboarding risk rating, on your own transactions file. FCA CP26/38, a consultation draft, names relying on transaction monitoring alone as poor practice and lists thresholds set without onboarding data as poor practice. The figures show what happened after onboarding. They do not check your onboarding checks, and they give no verdict on your process.
Each figure counts payments, not accounts: an account with many payments weighs more than one with few. A label count from 1 to 4, or one that would reveal such a count, is not shown.
By account age at the payment
- 0–7 days: 12,176 payments; a rule fired on 8,724 (716.5 per 1,000). Mature: 10,693. Fraud: 405 (37.9 per 1,000 mature payments). Mule label: 0. False alarms: 7,205 of 7,506 judged alerts (96.0%).
- 8–30 days: 12,605 payments; a rule fired on 9,063 (719.0 per 1,000). Mature: 11,144. Fraud: 429 (38.5 per 1,000 mature payments). Mule label: 0. False alarms: 7,564 of 7,897 judged alerts (95.8%).
- 31–90 days: 11,954 payments; a rule fired on 8,823 (738.1 per 1,000). Mature: 10,542. Fraud: 390 (37.0 per 1,000 mature payments). Mule label: 0. False alarms: 7,371 of 7,644 judged alerts (96.4%).
- 91–365 days: 11,409 payments; a rule fired on 8,001 (701.3 per 1,000). Mature: 10,088. Fraud: 460 (45.6 per 1,000 mature payments). Mule label: not shown: it would reveal a count under 5. False alarms: 6,617 of 6,974 judged alerts (94.9%).
- over 365 days: 11,017 payments; a rule fired on 7,699 (698.8 per 1,000). Mature: 9,739. Fraud: 394 (40.5 per 1,000 mature payments). Mule label: not shown: it would reveal a count under 5. False alarms: 6,398 of 6,689 judged alerts (95.6%).
- no usable account-opened value: 0 payments.
By your onboarding risk rating
The rating is taken as your transactions file records it on each payment; this review cannot tell an onboarding rating from a later re-rating.
- low: 20,490 payments; a rule fired on 14,663 (715.6 per 1,000). Mature: 18,160. Fraud: 696 (38.3 per 1,000 mature payments). Mule label: not shown: it would reveal a count under 5. False alarms: 12,236 of 12,747 judged alerts (96.0%).
- medium: 18,622 payments; a rule fired on 13,370 (718.0 per 1,000). Mature: 16,381. Fraud: 665 (40.6 per 1,000 mature payments). Mule label: 0. False alarms: 11,089 of 11,595 judged alerts (95.6%).
- high: 20,049 payments; a rule fired on 14,277 (712.1 per 1,000). Mature: 17,665. Fraud: 717 (40.6 per 1,000 mature payments). Mule label: not shown: it would reveal a count under 5. False alarms: 11,830 of 12,368 judged alerts (95.7%).
- no band value: 0 payments.
In this data, the fraud rate is not higher in each riskier band of your onboarding rating. This is a measurement on your payments, not a finding about your onboarding checks. This shows false alarms by your onboarding rating; it does not show why.
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) | Result | Source status | As of | Official 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 files | in force since 20.05.2026; 6 months to comply (about 20.11.2026) | 2026-11-11 | bank.gov.ua |
| Review every rule at least monthly by back-testing it. | Partly met | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| Metric 1: compare how often each rule fired with how many payments were actually stopped. | Partly met | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| Metric 2: share of fraud value that was prevented, out of all fraud value. | Partly met | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review. | Gap | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| Record a review decision for every rule: keep, adjust or cancel. | Partly met | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| Have evidence ready for a supervisor: documents, rules, risk markers. | Partly met | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| Show the acquirer's full name before an online payment; receipts show payee, commission, purpose and category code. | Not measurable from these files | in force since 20.05.2026; 6 months to comply (about 20.11.2026) | 2026-11-11 | bank.gov.ua |
| Reconcile payment operations every day. | Partly met | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| Acquiring for natural persons only for allowed categories, with the required data passed to the issuer. | Not measurable from these files | in force since 20.05.2026; 6 months to comply (about 20.11.2026) | 2026-11-11 | bank.gov.ua |
| Non-bank providers that acquire payments need an authorisation; the sanctions pause has ended. | Not measurable from these files | in force; grace period ended 02.09.2026 | 2026-11-11 | bank.gov.ua |
| Remote verification of natural persons uses the updated procedure with credit-bureau data. | Not measurable from these files | in force since 10.10.2026; 3 months to align internal procedures (about 10.01.2027) | 2026-11-11 | bank.gov.ua |
| Reports to the State Financial Monitoring Service go only through the e-cabinet, with numbered registers. | Not measurable from these files | in force since 10.10.2026; 3 months to align internal procedures (about 10.01.2027) | 2026-11-11 | bank.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 files | adopted by the Rada 28.10.2026; presidential signature not confirmed | 2026-11-11 | itd.rada.gov.ua |
Checks per EU requirements
| Requirement (our wording) | Result | Source status | As of | Official 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 files | agreed, not adopted (EU Payment Services Regulation; adoption expected by 12.2026) | 2026-11-11 | oeil.europarl.europa.eu |
Checks per UK requirements
| Requirement (our wording) | Result | Source status | As of | Official source |
|---|---|---|---|---|
| A claim may carry an excess of up to 100 GBP, never for vulnerable customers. | Not measurable from these files | in force | 2026-11-11 | psr.org.uk |
| Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice. | Partly met | guidance in force | 2026-11-11 | fca.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) | Result | Source status | As of | Official source |
|---|---|---|---|---|
| Analyse scenarios, rules and thresholds on an ongoing basis. | Partly met | in force | 2026-11-11 | dfs.ny.gov |
| Test rules before and after they go live. | Not measurable from these files | in force | 2026-11-11 | dfs.ny.gov |
| Tune and validate monitoring; justify each threshold. | Partly met | guidance | 2026-11-11 | bsaaml.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.
- Account takeover ATO
- A criminal gets into a customer's account and sends money out of it.
- Investment scam INVEST
- The customer is talked into paying into an investment that does not exist.
- Invoice redirection INVOICE
- A false or changed invoice makes the customer pay a criminal instead of the real supplier.
- Money mule MULE
- An account receives stolen money and passes it on for someone else.
- Purchase scam PURCHASE
- The customer pays for goods or services that never arrive.
- Safe-account scam SAFE
- A caller who poses as the bank tells the customer to move money to an account the caller controls.