WoWyrd · Rule review
Rule review: technical report
Client: Demo client (aml-hi, synthetic). Data: 2022-09-01 to 2022-09-18 (daily periods). Cut-off: 2022-09-18 (given with --cutoff). Generated: 2026-11-20 10:02 UTC.
Internal report. Do not share it outside your firm.
Method and definitions
The review measures what the client's own engine logged. It does not run the client's rules. To compare your own rule definitions with your engine's log, give the collector a rule file: Download an example rule file (JSON, with a note on every key; replace its example consent line before you use it). Label delay: 7 days. Hits newer than 2022-09-18 minus the label delay are not yet mature. One alert takes 6 analyst minutes at 0.80 USD per minute. A declined payment that was not fraud costs 4.00 USD in customer friction. The client entered these costs. Every cost in this report is an estimate from them.
- A hit is a transaction on which the rule fired, from the client's rule-hit log. An alert is a transaction with at least one hit.
- A hit is mature when the transaction is older than the client's stated label delay at the cut-off, so a fraud label had time to arrive. Immature hits are reported, never counted as false alarms or as friction.
- The label of a transaction is the label row with the latest date known at or before the cut-off. A later label that arrives after the cut-off is not used.
- A declined payment has no outcome (selective labels): its hits are counted and reported, and left out of precision and false-alarm counts.
- Evaluable = mature and not declined. Caught = evaluable with a fraud label. False alarm = evaluable with no fraud and no disputed label. Disputed = evaluable with a disputed label: it is neither caught nor a false alarm, it is shown on its own, and it is left out of precision.
- Precision = caught / (caught + false alarms). Recall share = caught / all evaluable fraud in the period.
- Alert cost: one alert per transaction with any hit, whatever the number of rules; a false alarm costs analyst minutes x cost per minute, shared equally among the rules that fired on it. Friction: a mature declined payment with no fraud and no disputed label costs the client's friction cost, shared the same way.
- Decay: precision of the last three mature periods is at most half of the three before (needs six periods).
Totals
| Measure | Value |
|---|---|
| Transactions | 58,331 |
| Alerts (transactions with at least one hit) | 53,483 |
| Alerts not yet mature (newer than the label delay) | 143 |
| Alerts on declined payments (no outcome; left out of precision) | 2,129 |
| Confirmed fraud (label known by the cut-off) | 967 |
| Confirmed fraud with at least one hit | 928 |
| Evaluable fraud (mature, not declined) | 948 |
| False alarms | 50,302 |
| Declined payments with no fraud or disputed label (friction) | 2,110 |
| False-alarm cost (estimate) | 249,889.60 USD |
| Rule-hit rows that matched a transaction | 58,331 of 58,331 (100.0%) |
| Label rows that matched a transaction | 1,076 of 1,076 (100.0%) |
Source: transactions, rule-hit log and labels files, 2022-09-01 to 2022-09-18.
Per-rule metrics
Rules are sorted by false-alarm cost, highest first. The trend line shows precision per period.
| Rule | Hits | Not yet mature | Declined | Evaluable | Caught | False alarms | Precision | Recall share | Cost (USD) | Decayed | Precision trend |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Money sent to 5+ different recipients within 5 days (fan-out) tp_u21_fan_out_5_benef_5d Finds one sender spreading money to many receivers in a short time. | 41,258 | 20 | 2,093 | 39,145 | 211 | 38,934 | 0.5% | 22.3% | 95,904.24 USD | No | |
| Transfer above 500 USD tp_u21_transfer_over_500 Flags every transfer over a low fixed amount, so analysts see most mid-size transfers. | 36,685 | 141 | 2,112 | 34,432 | 837 | 33,595 | 2.4% | 88.3% | 77,428.24 USD | No | |
| Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24h Finds an account that collects several small payments and passes most of the money on at once. | 15,845 | 0 | 1,974 | 13,871 | 66 | 13,805 | 0.5% | 7.0% | 23,994.16 USD | No | |
| Money in, then almost all of it sent on within 3 days (layering) tp_u21_layering_10k_90pct_3d Finds an account that receives a large sum and quickly passes nearly all of it to other people. | 15,502 | 26 | 1,999 | 13,477 | 119 | 13,358 | 0.9% | 12.6% | 23,275.53 USD | No | |
| Single payment above 9,000 USD tp_u21_large_txn_9k Flags any one large payment for a closer look. | 12,042 | 73 | 2,006 | 9,963 | 345 | 9,618 | 3.5% | 36.4% | 17,737.70 USD | No | |
| Money from 5+ different senders into one account within 5 days (fan-in) tp_ffiec_fan_in_5_senders_5d Finds one account that collects money from many people, as a collection or mule account does. | 1,588 | 27 | 7 | 1,554 | 100 | 1,454 | 6.4% | 10.5% | 4,322.97 USD | No | |
| 10+ mid-size payments in 5 days, over 20,000 USD in total tp_u21_stats_10tx_1k3k_5d Finds a burst of many similar mid-size payments that add up to a large total. | 1,771 | 3 | 102 | 1,666 | 31 | 1,635 | 1.9% | 3.3% | 3,991.46 USD | No | |
| More than 2 wire transfers in 7 days tp_u21_wire_count_gt2_7d Finds a sender who uses wire transfers unusually often. | 653 | 0 | 125 | 528 | 0 | 528 | 0.0% | 0.0% | 1,333.86 USD | No | |
| 20+ small payments in 5 days, over 20,000 USD in total tp_u21_stats_20tx_0_1k_5d Finds many small payments that together move a large sum. | 349 | 1 | 24 | 324 | 2 | 322 | 0.6% | 0.2% | 698.93 USD | No | |
| Wire transfers above 4,999 USD in total within 7 days tp_u21_wire_total_gt4999_7d Finds a sender who moves a large total by wire in one week. | 505 | 0 | 137 | 368 | 0 | 368 | 0.0% | 0.0% | 625.00 USD | No | |
| Repeated payments just under 10,000 USD (structuring) tp_u21_structuring_9k_10k_5d Finds payments kept just below a reporting limit to avoid a report. | 554 | 1 | 246 | 307 | 7 | 300 | 2.3% | 0.7% | 577.51 USD | No |
Hits and precision per period
Each cell: hits / precision in that period.
| Rule | 2022-09-01 | 2022-09-02 | 2022-09-03 | 2022-09-04 | 2022-09-05 | 2022-09-06 | 2022-09-07 | 2022-09-08 | 2022-09-09 | 2022-09-10 | 2022-09-11 | 2022-09-12 | 2022-09-13 | 2022-09-14 | 2022-09-15 | 2022-09-16 | 2022-09-17 | 2022-09-18 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Money from 5+ different senders into one account within 5 days (fan-in) tp_ffiec_fan_in_5_senders_5d Finds one account that collects money from many people, as a collection or mule account does. | 175 / 2.3% | 229 / 4.4% | 66 / 13.8% | 112 / 12.5% | 232 / 8.7% | 97 / 12.4% | 61 / 6.6% | 88 / 4.5% | 302 / 4.0% | 198 / 5.1% | 9 / 100.0% | 8 / no data | 4 / no data | 7 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24h Finds an account that collects several small payments and passes most of the money on at once. | 1,715 / 0.7% | 5,788 / 0.1% | 1,406 / 0.2% | 52 / 2.1% | 150 / 4.4% | 264 / 1.8% | 267 / 3.5% | 269 / 5.4% | 4,468 / 0.3% | 1,466 / 0.6% | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| Money sent to 5+ different recipients within 5 days (fan-out) tp_u21_fan_out_5_benef_5d Finds one sender spreading money to many receivers in a short time. | 5,078 / 0.4% | 6,540 / 0.4% | 1,859 / 0.6% | 1,867 / 0.8% | 4,735 / 0.3% | 4,675 / 0.5% | 4,598 / 0.5% | 4,550 / 0.6% | 5,499 / 0.6% | 1,827 / 1.2% | 19 / 70.0% | 6 / no data | 3 / no data | 2 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| Single payment above 9,000 USD tp_u21_large_txn_9k Flags any one large payment for a closer look. | 2,182 / 0.8% | 2,216 / 2.1% | 432 / 12.6% | 439 / 6.4% | 1,172 / 3.5% | 1,142 / 4.1% | 1,135 / 3.9% | 1,172 / 3.4% | 1,610 / 3.3% | 457 / 12.7% | 31 / 75.0% | 22 / no data | 15 / no data | 9 / no data | 1 / no data | 3 / no data | 4 / no data | 0 / no data |
| Money in, then almost all of it sent on within 3 days (layering) tp_u21_layering_10k_90pct_3d Finds an account that receives a large sum and quickly passes nearly all of it to other people. | 1,221 / 0.6% | 3,928 / 0.3% | 1,727 / 0.6% | 1,356 / 0.9% | 2,157 / 0.4% | 249 / 5.1% | 339 / 3.0% | 405 / 4.5% | 2,743 / 0.7% | 1,339 / 1.2% | 22 / 66.7% | 7 / no data | 6 / no data | 3 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| 10+ mid-size payments in 5 days, over 20,000 USD in total tp_u21_stats_10tx_1k3k_5d Finds a burst of many similar mid-size payments that add up to a large total. | 28 / 3.7% | 95 / 1.1% | 36 / 5.6% | 57 / 3.5% | 167 / 2.4% | 248 / 2.1% | 300 / 2.5% | 321 / 1.0% | 374 / 0.3% | 142 / 3.9% | 0 / no data | 3 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| 20+ small payments in 5 days, over 20,000 USD in total tp_u21_stats_20tx_0_1k_5d Finds many small payments that together move a large sum. | 0 / no data | 0 / no data | 0 / no data | 6 / 0.0% | 19 / 0.0% | 33 / 0.0% | 42 / 0.0% | 86 / 2.6% | 117 / 0.0% | 45 / 0.0% | 1 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| Repeated payments just under 10,000 USD (structuring) tp_u21_structuring_9k_10k_5d Finds payments kept just below a reporting limit to avoid a report. | 49 / 0.0% | 92 / 0.0% | 24 / 0.0% | 26 / 0.0% | 65 / 2.3% | 63 / 3.6% | 65 / 3.6% | 64 / 0.0% | 80 / 7.4% | 25 / 0.0% | 0 / no data | 0 / no data | 1 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| Transfer above 500 USD tp_u21_transfer_over_500 Flags every transfer over a low fixed amount, so analysts see most mid-size transfers. | 5,504 / 1.0% | 6,073 / 1.4% | 1,476 / 4.7% | 1,528 / 4.8% | 3,838 / 2.6% | 3,768 / 2.7% | 3,761 / 2.3% | 3,840 / 2.7% | 5,046 / 2.1% | 1,689 / 5.7% | 59 / 76.2% | 44 / no data | 29 / no data | 18 / no data | 3 / no data | 3 / no data | 5 / no data | 1 / no data |
| More than 2 wire transfers in 7 days tp_u21_wire_count_gt2_7d Finds a sender who uses wire transfers unusually often. | 3 / 0.0% | 33 / 0.0% | 40 / 0.0% | 40 / 0.0% | 98 / 0.0% | 98 / 0.0% | 98 / 0.0% | 98 / 0.0% | 105 / 0.0% | 40 / 0.0% | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
| Wire transfers above 4,999 USD in total within 7 days tp_u21_wire_total_gt4999_7d Finds a sender who moves a large total by wire in one week. | 54 / 0.0% | 86 / 0.0% | 23 / 0.0% | 25 / 0.0% | 54 / 0.0% | 55 / 0.0% | 57 / 0.0% | 57 / 0.0% | 69 / 0.0% | 25 / 0.0% | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data | 0 / no data |
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: give it this folder with --previous.
Overlaps between rules
Rules that never fired
| Rule | Input fields | Status |
|---|---|---|
| Large payment on an account less than 30 days old tp_ffiec_new_account_large_30d Finds big money movement on a newly opened account. | amount, account_age_days | Input absent: the transactions file has no account_age_days |
| Repeated large round-number transfers tp_ffiec_round_amounts Finds a sender who keeps sending large, round amounts (a common money-laundering sign). | ts, sender_id, receiver_id, amount | Input present; the rule never fired |
| Dormant account suddenly moves more than 5,000 USD tp_u21_dormant_100d_5k Finds an account that was quiet for months and then starts moving money, as when a taken-over or sold account is put to use. | ts, sender_id, receiver_id, amount | Input present; the rule never fired |
| Spending in the last 3 days doubles the monthly norm tp_u21_hist_deviation_3d_31d Finds a sender whose recent outgoing volume jumps far above their own usual level. | ts, sender_id, receiver_id, amount | Input present; the rule never fired |
Proposals
No written effectiveness threshold was given. The retire line is the fraud rate of all payments with a known outcome.
Effects are backtests on past data, not forecasts.
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
Reference REC-a9097de7. Quote this reference in your change record.
Retire the ruleConfidence: mediumPriority: 62.17
Rules
- Money sent to 5+ different recipients within 5 days (fan-out) tp_u21_fan_out_5_benef_5dFinds one sender spreading money to many receivers in a short time.
Expected effect (backtest on past data): 7,624 fewer alerts, 40 caught fraud cases lost, 36,403.20 USD saved (estimate).
Evidence
- Rule Money sent to 5+ different recipients within 5 days (fan-out) fired 41,258 times. 39,145 alerts have a known outcome; 211 were fraud (0.5%).
- The line is the fraud rate of all payments with a known outcome, 1.7% (948 of 56,056).
- On 7,624 payments only this rule fired. 40 of them were fraud that no other rule caught. 0 are too recent to judge.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,093 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 20 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review) and UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel) come from an NBU draft resolution. It is a draft, not law.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review)
- UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel)
- UK-FCA-02 (Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice)
- US-FFIEC-01 (Tune and validate monitoring; justify each threshold)
- US-NYDFS-01 (Analyse scenarios, rules and thresholds on an ongoing basis)
Retire rule More than 2 wire transfers in 7 days: 0.0% of its 528 alerts with a known outcome were fraud
Reference REC-0e97fd0f. Quote this reference in your change record.
Retire the ruleConfidence: highPriority: 60.08
Rules
- More than 2 wire transfers in 7 days tp_u21_wire_count_gt2_7dFinds a sender who uses wire transfers unusually often.
Expected effect (backtest on past data): 132 fewer alerts, 0 caught fraud cases lost, 633.60 USD saved (estimate).
Evidence
- Rule More than 2 wire transfers in 7 days fired 653 times. 528 alerts have a known outcome; 0 were fraud (0.0%).
- The line is the fraud rate of all payments with a known outcome, 1.7% (948 of 56,056).
- On 132 payments only this rule fired. 0 of them were fraud that no other rule caught. 0 are too recent to judge.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 125 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review) and UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel) come from an NBU draft resolution. It is a draft, not law.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review)
- UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel)
- UK-FCA-02 (Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice)
- US-FFIEC-01 (Tune and validate monitoring; justify each threshold)
- US-NYDFS-01 (Analyse scenarios, rules and thresholds on an ongoing basis)
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
Reference REC-8623ab86. Quote this reference in your change record.
Retire the ruleConfidence: highPriority: 60.02
Rules
- 20+ small payments in 5 days, over 20,000 USD in total tp_u21_stats_20tx_0_1k_5dFinds many small payments that together move a large sum.
Expected effect (backtest on past data): 29 fewer alerts, 0 caught fraud cases lost, 139.20 USD saved (estimate).
Evidence
- Rule 20+ small payments in 5 days, over 20,000 USD in total fired 349 times. 324 alerts have a known outcome; 2 were fraud (0.6%).
- The line is the fraud rate of all payments with a known outcome, 1.7% (948 of 56,056).
- On 29 payments only this rule fired. 0 of them were fraud that no other rule caught. 0 are too recent to judge.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 24 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 1 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review) and UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel) come from an NBU draft resolution. It is a draft, not law.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review)
- UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel)
- UK-FCA-02 (Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice)
- US-FFIEC-01 (Tune and validate monitoring; justify each threshold)
- US-NYDFS-01 (Analyse scenarios, rules and thresholds on an ongoing basis)
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
Reference REC-5f92ad0d. Quote this reference in your change record.
Retire the ruleConfidence: mediumPriority: 60.01
Rules
- Money in, then almost all of it sent on within 3 days (layering) tp_u21_layering_10k_90pct_3dFinds an account that receives a large sum and quickly passes nearly all of it to other people.
Expected effect (backtest on past data): 109 fewer alerts, 1 caught fraud cases lost, 518.40 USD saved (estimate).
Evidence
- Rule Money in, then almost all of it sent on within 3 days (layering) fired 15,502 times. 13,477 alerts have a known outcome; 119 were fraud (0.9%).
- The line is the fraud rate of all payments with a known outcome, 1.7% (948 of 56,056).
- On 109 payments only this rule fired. 1 of them were fraud that no other rule caught. 0 are too recent to judge.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 1,999 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 26 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review) and UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel) come from an NBU draft resolution. It is a draft, not law.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review)
- UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel)
- UK-FCA-02 (Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice)
- US-FFIEC-01 (Tune and validate monitoring; justify each threshold)
- US-NYDFS-01 (Analyse scenarios, rules and thresholds on an ongoing basis)
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
Reference REC-c96ac8db. Quote this reference in your change record.
Retire the ruleConfidence: highPriority: 60.0
Rules
- Wire transfers above 4,999 USD in total within 7 days tp_u21_wire_total_gt4999_7dFinds a sender who moves a large total by wire in one week.
Expected effect (backtest on past data): 2 fewer alerts, 0 caught fraud cases lost, 9.60 USD saved (estimate).
Evidence
- Rule Wire transfers above 4,999 USD in total within 7 days fired 505 times. 368 alerts have a known outcome; 0 were fraud (0.0%).
- The line is the fraud rate of all payments with a known outcome, 1.7% (948 of 56,056).
- On 2 payments only this rule fired. 0 of them were fraud that no other rule caught. 0 are too recent to judge.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 137 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review) and UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel) come from an NBU draft resolution. It is a draft, not law.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review)
- UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel)
- UK-FCA-02 (Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice)
- US-FFIEC-01 (Tune and validate monitoring; justify each threshold)
- US-NYDFS-01 (Analyse scenarios, rules and thresholds on an ongoing basis)
Retire rule Many small payments in, then sent out within a day: 0.5% of its 13,871 alerts with a known outcome were fraud
Reference REC-be451688. Quote this reference in your change record.
Retire the ruleConfidence: mediumPriority: 59.97
Rules
- Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24hFinds an account that collects several small payments and passes most of the money on at once.
Expected effect (backtest on past data): 142 fewer alerts, 2 caught fraud cases lost, 672.00 USD saved (estimate).
Evidence
- Rule Many small payments in, then sent out within a day fired 15,845 times. 13,871 alerts have a known outcome; 66 were fraud (0.5%).
- The line is the fraud rate of all payments with a known outcome, 1.7% (948 of 56,056).
- On 142 payments only this rule fired. 2 of them were fraud that no other rule caught. 0 are too recent to judge.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 1,974 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review) and UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel) come from an NBU draft resolution. It is a draft, not law.
- UA-NBU-04 (Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review)
- UA-NBU-05 (Record a review decision for every rule: keep, adjust or cancel)
- UK-FCA-02 (Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice)
- US-FFIEC-01 (Tune and validate monitoring; justify each threshold)
- US-NYDFS-01 (Analyse scenarios, rules and thresholds on an ongoing basis)
Add a rule for: Gambling winnings arrive with no deposits, then card transfers follow
Reference REC-446cbd14. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 50.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_id, mcc, operation_type.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S07 (Gambling winnings arrive with no deposits, then card transfers follow) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S07 (Gambling winnings arrive with no deposits, then card transfers follow)
Add a rule for: Large loans are taken and repaid again and again
Reference REC-ba91d001. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 50.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_id, operation_type, amount.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S05 (Large loans are taken and repaid again and again) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S05 (Large loans are taken and repaid again and again)
Add a rule for: One type of operation makes up an unusual share of a user's activity
Reference REC-5aaedf3e. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 50.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_id, operation_type, amount.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S02 (One type of operation makes up an unusual share of a user's activity) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S02 (One type of operation makes up an unusual share of a user's activity)
Add a rule for: Payment purposes do not fit the merchant's category code
Reference REC-fb8e4691. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 50.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: mcc, payment_purpose.
- None of the 15 rules in your catalogue matches this typology by name.
- It cannot be covered on this data: the transactions file has no category-code or no payment-purpose column (see UA-NBU51-01 (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)).
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S11 (Payment purposes do not fit the merchant's category code) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S11 (Payment purposes do not fit the merchant's category code)
- UA-NBU51-01 (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)
Add a rule for: Regular transfers to a personal account look like business activity
Reference REC-0ed6eeef. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 50.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: account_type, counterparty_id, ts, amount.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S08 (Regular transfers to a personal account look like business activity) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S08 (Regular transfers to a personal account look like business activity)
Add a rule for: A large first payment to a payee never paid before
Reference REC-cb3579dc. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: payer_id, payee_id, amount.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UK-FINANCE
- UK-PSR
Add a rule for: A new merchant's volume is far above similar merchants, then the merchant closes
Reference REC-aa6aa855. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: merchant_id, mcc, merchant_onboarded_at, amount.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S09 (A new merchant's volume is far above similar merchants, then the merchant closes) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S09 (A new merchant's volume is far above similar merchants, then the merchant closes)
Add a rule for: Activity at hours unusual for the customer
Reference REC-bae797f8. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_id, ts.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- NBU-DRAFT
Add a rule for: An older customer suddenly sends a large amount to a new payee
Reference REC-9a8e640b. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_age, payee_id, amount.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- FINCEN
Add a rule for: Contacts, device, apps, IMEI, operating system or network address change often
Reference REC-5bdeada7. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_id, device_id, ip, contact_changed_at.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S12 (Contacts, device, apps, IMEI, operating system or network address change often) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S12 (Contacts, device, apps, IMEI, operating system or network address change often)
Add a rule for: Credits from many different banks into one account
Reference REC-e2af60b6. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: payee_id, payer_bank.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- FIU-UA
- FINCEN
Add a rule for: Many senders' accounts share one beneficiary
Reference REC-8380b3b9. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: payer_id, payee_id.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- WOWYRD-SPIKE
- FINCEN
Add a rule for: Merchant account inflows mirror its outflows (transit)
Reference REC-503ead70. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: merchant_id, direction, amount.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S10 (Merchant account inflows mirror its outflows (transit)) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S10 (Merchant account inflows mirror its outflows (transit))
Add a rule for: One device fingerprint is used by unrelated users
Reference REC-265cee82. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: device_id, customer_id.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S13 (One device fingerprint is used by unrelated users) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S13 (One device fingerprint is used by unrelated users)
Add a rule for: One user holds many more accounts or cards than similar users
Reference REC-8cf723d6. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_id, account_id.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S01 (One user holds many more accounts or cards than similar users) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S01 (One user holds many more accounts or cards than similar users)
Add a rule for: The payee name does not match and the payment still goes
Reference REC-87ecb24a. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: name_check_result.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UK-PSR
- EU-PSR
Add a rule for: The payment reference mentions investment, crypto or a 'safe account'
Reference REC-19d324eb. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: payment_purpose.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UK-FINANCE
Add a rule for: Transfers to or from high-risk jurisdictions
Reference REC-9b484507. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: counterparty_country.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- FATF-REF
- FFIEC-APPF
Add a rule for: Two operations are too far apart to travel between in the time
Reference REC-6d6b4334. Quote this reference in your change record.
Add a missing fraud typeConfidence: mediumPriority: 30.0
Rules: none.
Expected effect: no effect estimate for this proposal.
Evidence
- Needs these data fields: customer_id, geo_location, ts.
- None of the 15 rules in your catalogue matches this typology by name.
- Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days.
Caveats
- Selective labels: 2,131 alerts were on declined payments. Their outcome is unknown, so they are left out of precision and of fraud caught.
- Label maturity: 143 alerts are newer than the 7-day label delay. They are not counted as false alarms.
- Short history: the data covers 1 calendar month(s). Trends need at least 6.
- Synthetic data: the transactions, labels and unit costs are demo values, not a client's data.
- UA-NBU-S14 (Two operations are too far apart to travel between in the time) is a sign from an NBU draft resolution. It is a draft, not law.
- UA-NBU-S14 (Two operations are too far apart to travel between in the time)
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).
| Tool | Rules | Alerts | Caught | Catch rate | False alarms | Precision | False-alarm cost (estimate) | Only this tool caught |
|---|---|---|---|---|---|---|---|---|
| Transaction monitoring (example) | 7 | 43,792 | 287 | 30.3% | 41,342 | 0.7% | 121,748.27 USD | 50 |
| In-house rules (example) | 2 | 36,685 | 837 | 88.3% | 33,595 | 2.4% | 93,887.87 USD | 508 |
| AML monitoring (example) | 2 | 17,421 | 166 | 17.5% | 15,252 | 1.1% | 34,253.47 USD | 7 |
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 type | Transaction monitoring (example) | In-house rules (example) | AML monitoring (example) |
|---|---|---|---|
| no type given | 129 (48 only) | 329 (223 only) | 65 (7 only) |
| BIPARTITE | 8 (0 only) | 47 (34 only) | 8 (0 only) |
| CYCLE | 10 (0 only) | 41 (29 only) | 5 (0 only) |
| FAN-IN | 11 (0 only) | 50 (20 only) | 21 (0 only) |
| FAN-OUT | 54 (2 only) | 75 (21 only) | 17 (0 only) |
| GATHER-SCATTER | 24 (0 only) | 81 (40 only) | 19 (0 only) |
| RANDOM | 8 (0 only) | 40 (32 only) | 2 (0 only) |
| SCATTER-GATHER | 19 (0 only) | 94 (56 only) | 22 (0 only) |
| STACK | 24 (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)
| Tool | Alerts removed | Caught fraud cases lost | Cost saved (estimate) |
|---|---|---|---|
| Transaction monitoring (example) | 10,868 | 50 | 51,918.40 USD |
| In-house rules (example) | 7,562 | 508 | 33,451.20 USD |
| AML monitoring (example) | 584 | 7 | 2,764.80 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.
- Transaction monitoring (example) fired on 2,129 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 2,112 payments that were declined. Fraud stopped by a decline has no outcome, so this tool's real value may be higher than shown.
- AML monitoring (example): on your history, almost all fraud this tool caught was also caught by your other tools (7 of 166 only by this tool). Before you change anything, check what this data cannot show (see the limits).
- AML monitoring (example) fired on 1,976 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.
- On this history, your current tools together caught most of the fraud: they missed 39 of 948 mature fraud cases with a known outcome. The proposals in this report are fine-tuning, not a gap.
Your tools over time
Two equal windows: the latest 3 days old enough for labels, against the 3 before. Each share is pooled over its window, so a small day weighs little. Precision is compared only with 30 or more alerts with a known outcome on each side, catch rate only with 30 or more fraud cases with a known outcome on each side. A change is flagged when it is 10 points or more and a two-proportion test gives |z| of 1.96 or more. The 10 points and the 1.96 are our defaults, not a regulatory number. The alert rate is shown, never flagged: a change in traffic moves it with no change in the tool.
| Tool | Window | Alerts | Alerts per 1,000 payments | Alerts with a known outcome | Caught | Precision | Fraud cases with a known outcome | Catch rate |
|---|---|---|---|---|---|---|---|---|
| Transaction monitoring (example) | 2022-09-05 to 2022-09-07 | 14,856 | 793.7 | 14,725 | 92 | 0.6% | 320 | 28.7% |
| Transaction monitoring (example) | 2022-09-08 to 2022-09-10 | 12,887 | 762.4 | 12,096 | 107 | 0.9% | 323 | 33.1% |
| In-house rules (example) | 2022-09-05 to 2022-09-07 | 11,367 | 607.3 | 11,242 | 285 | 2.5% | 320 | 89.1% |
| In-house rules (example) | 2022-09-08 to 2022-09-10 | 10,575 | 625.6 | 9,793 | 283 | 2.9% | 323 | 87.6% |
| AML monitoring (example) | 2022-09-05 to 2022-09-07 | 1,067 | 57.0 | 979 | 54 | 5.5% | 320 | 16.9% |
| AML monitoring (example) | 2022-09-08 to 2022-09-10 | 6,788 | 401.6 | 6,046 | 55 | 0.9% | 323 | 17.0% |
- Transaction monitoring (example): precision and catch rate did not change by more than our limit between 2022-09-05 to 2022-09-07 and 2022-09-08 to 2022-09-10.
- In-house rules (example): precision and catch rate did not change by more than our limit between 2022-09-05 to 2022-09-07 and 2022-09-08 to 2022-09-10.
- AML monitoring (example): precision and catch rate did not change by more than our limit between 2022-09-05 to 2022-09-07 and 2022-09-08 to 2022-09-10.
Per day
| Tool | Period | Alerts | Alerts per 1,000 payments | Precision | Catch rate |
|---|---|---|---|---|---|
| Transaction monitoring (example) | 2022-09-05 | 4,968 | 789.1 | 0.5% | 21.6% |
| Transaction monitoring (example) | 2022-09-06 | 4,957 | 796.9 | 0.7% | 30.4% |
| Transaction monitoring (example) | 2022-09-07 | 4,931 | 795.2 | 0.7% | 35.1% |
| Transaction monitoring (example) | 2022-09-08 | 4,924 | 783.2 | 0.9% | 36.1% |
| Transaction monitoring (example) | 2022-09-09 | 5,971 | 757.3 | 0.7% | 35.5% |
| Transaction monitoring (example) | 2022-09-10 | 1,992 | 729.4 | 1.4% | 26.6% |
| In-house rules (example) | 2022-09-05 | 3,838 | 609.6 | 2.6% | 87.4% |
| In-house rules (example) | 2022-09-06 | 3,768 | 605.8 | 2.7% | 90.2% |
| In-house rules (example) | 2022-09-07 | 3,761 | 606.5 | 2.3% | 89.7% |
| In-house rules (example) | 2022-09-08 | 3,840 | 610.8 | 2.7% | 85.7% |
| In-house rules (example) | 2022-09-09 | 5,046 | 639.9 | 2.1% | 87.3% |
| In-house rules (example) | 2022-09-10 | 1,689 | 618.5 | 5.7% | 90.4% |
| AML monitoring (example) | 2022-09-05 | 378 | 60.0 | 7.1% | 23.4% |
| AML monitoring (example) | 2022-09-06 | 361 | 58.0 | 4.9% | 14.3% |
| AML monitoring (example) | 2022-09-07 | 328 | 52.9 | 4.2% | 12.4% |
| AML monitoring (example) | 2022-09-08 | 357 | 56.8 | 5.1% | 13.4% |
| AML monitoring (example) | 2022-09-09 | 4,769 | 604.8 | 0.5% | 20.0% |
| AML monitoring (example) | 2022-09-10 | 1,662 | 608.6 | 1.2% | 18.1% |
A day with fewer than 30 alerts with a known outcome shows "too few" for its precision. No flag comes from a single day.
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.
Below-the-line sample (AML rules)
No rule file was given, so there is no below-the-line sample. Give a rule file and mark your AML rules with "kind": "aml": Download an example rule file (JSON, with a note on every key; replace its example consent line before you use it).
Coverage by fraud type
Fraud types present in your labels
| Fraud type | Labelled cases | Caught | Missed | Library types it matches | Your rules' coverage | WoWyrd |
|---|---|---|---|---|---|---|
| Spread, then collect | 98 | 97 | 1 | Money comes in and leaves fast, little balance stays (UA-NBU-S06), Most of an incoming amount leaves again within hours (OR-02) | Covered | WoWyrd rule available: Money leaves soon after it arrives rapid_pass_through |
| Layers of accounts | 86 | 83 | 3 | none | Covered | WoWyrd rule: planned |
| Collect, then spread | 84 | 83 | 1 | Money comes in and leaves fast, little balance stays (UA-NBU-S06), Most of an incoming amount leaves again within hours (OR-02), Many small credits, then one large debit (OR-13) | Covered | WoWyrd rule available: Money leaves soon after it arrives rapid_pass_through; Many small credits, then one large payout many_small_credits_then_large_payout |
| One out to many (fan-out) | 83 | 83 | 0 | One payer sends to far more payees than similar payers (UA-NBU-S15), One account pays many new beneficiaries (OR-07) | Covered | WoWyrd rule available: One account pays many different payees account_many_payees |
| Many into one (fan-in) | 54 | 52 | 2 | Many payers send to one payee, far more than for similar payees (UA-NBU-S16), Many different senders pay one account within a short time (OR-01) | Covered | WoWyrd rule available: Many senders pay one account inbound_sender_fan_in; One payee shared by several customers beneficiary_reuse |
| Two groups paying each other | 49 | 47 | 2 | none | Covered | WoWyrd rule: planned |
| Money in a circle | 44 | 43 | 1 | Money goes round in a circle between accounts within days (OR-11) | Covered | WoWyrd rule: planned |
| Random hops | 41 | 40 | 1 | none | Covered | WoWyrd rule: planned |
| Type not given | 428 | 400 | 28 | none | Unknown | 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. The rules column lists catalogue rules whose names match the type.
| Library type | ID | Your rules whose names match | Sources | WoWyrd |
|---|---|---|---|---|
| One user holds many more accounts or cards than similar users | UA-NBU-S01 | none | UA-NBU-S01 | WoWyrd rule: planned |
| One type of operation makes up an unusual share of a user's activity | UA-NBU-S02 | none | UA-NBU-S02 | WoWyrd rule available: One type of operation dominates an account operation_type_concentration |
| Many operations of one type in a short time, incoming or outgoing | UA-NBU-S03 | Money from 5+ different senders into one account within 5 days (fan-in) tp_ffiec_fan_in_5_senders_5d | UA-NBU-S03 | WoWyrd rule available: Many requests from one account in an hour, then a payout payout_velocity_1h; A burst of operations of one type same_operation_type_burst |
| Balance stays low although large amounts pass through | UA-NBU-S04 | Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24h | UA-NBU-S04 | WoWyrd rule available: Large amounts pass through an account that keeps a low balance low_balance_high_turnover |
| Large loans are taken and repaid again and again | UA-NBU-S05 | none | UA-NBU-S05 | WoWyrd rule available: Large loans taken and repaid again and again loan_issue_repayment_churn |
| Gambling winnings arrive with no deposits, then card transfers follow | UA-NBU-S07 | none | UA-NBU-S07 | WoWyrd rule available: Gambling winnings with no gambling deposits gambling_winnings_without_deposits |
| Regular transfers to a personal account look like business activity | UA-NBU-S08 | none | UA-NBU-S08 | WoWyrd rule available: A personal account paid by many payers personal_account_business_activity |
| A new merchant's volume is far above similar merchants, then the merchant closes | UA-NBU-S09 | none | UA-NBU-S09 | WoWyrd rule available: A merchant with little history suddenly busy low_history_merchant_spike |
| Merchant account inflows mirror its outflows (transit) | UA-NBU-S10 | none | UA-NBU-S10 | WoWyrd rule available: A business account pays out almost all it receives business_account_transit |
| Payment purposes do not fit the merchant's category code | UA-NBU-S11 | none | UA-NBU-S11 | WoWyrd rule available: Payment purpose does not fit the merchant's business payment_purpose_atypical_for_mcc; Card payment to a person without category or purpose acquiring_to_person_missing_data |
| Contacts, device, apps, IMEI, operating system or network address change often | UA-NBU-S12 | none | UA-NBU-S12 | WoWyrd rule available: Payout right after an email or phone change contact_change_to_payout; One session from several network addresses session_multiple_ips; One account used from many devices account_many_devices |
| One device fingerprint is used by unrelated users | UA-NBU-S13 | none | UA-NBU-S13 | WoWyrd rule available: One device used by several customers multi_account_device |
| Two operations are too far apart to travel between in the time | UA-NBU-S14 | none | UA-NBU-S14 | WoWyrd rule available: Locations too far apart for the time between them impossible_travel |
| A new account gets large or many credits soon after opening | OR-03 | Large payment on an account less than 30 days old tp_ffiec_new_account_large_30d | UNIT21, UK-FINANCE | WoWyrd rule available: A new account receives a large credit new_account_large_incoming_credit; A new account paid by several people new_account_inbound_fan_in |
| A dormant account suddenly moves large amounts | OR-04 | Dormant account suddenly moves more than 5,000 USD tp_u21_dormant_100d_5k | FFIEC-APPF | WoWyrd rule: planned |
| Repeated amounts just under a reporting or limit threshold | OR-05 | 10+ mid-size payments in 5 days, over 20,000 USD in total tp_u21_stats_10tx_1k3k_5d, 20+ small payments in 5 days, over 20,000 USD in total tp_u21_stats_20tx_0_1k_5d, Repeated payments just under 10,000 USD (structuring) tp_u21_structuring_9k_10k_5d | FFIEC-APPF | WoWyrd rule available: Payments just under a limit just_below_threshold_payment; Many small payments from one account add up to a large sum amount_structuring_account; Many small payments to one payee add up to a large sum amount_structuring_beneficiary |
| Repeated round amounts with no business reason | OR-06 | Repeated large round-number transfers tp_ffiec_round_amounts | FFIEC-APPF | WoWyrd rule available: Several payments in large round amounts repeated_round_amounts |
| Outgoing payments per hour above the customer's usual level | OR-08 | Spending in the last 3 days doubles the monthly norm tp_u21_hist_deviation_3d_31d | UNIT21, EBA-GL-2021-02 | WoWyrd rule available: More payments in an hour than the customer usually makes high_customer_velocity_1h; Many requests from one account in an hour, then a payout payout_velocity_1h |
| A large first payment to a payee never paid before | OR-09 | none | UK-FINANCE, UK-PSR | WoWyrd rule available: A large payment to a payee added just before new_payee_high_amount |
| Many senders' accounts share one beneficiary | OR-10 | none | WOWYRD-SPIKE, FINCEN | WoWyrd rule available: One payee shared by several customers beneficiary_reuse |
| An amount far above the customer's own history | OR-12 | Spending in the last 3 days doubles the monthly norm tp_u21_hist_deviation_3d_31d | EBA-GL-2021-02, NBU-DRAFT | WoWyrd rule available: A payment far above the customer's usual amount amount_far_above_customer_average |
| Credits from many different banks into one account | OR-14 | none | FIU-UA, FINCEN | WoWyrd rule available: Credits from many different banks into one account inbound_from_many_banks |
| Transfers to or from high-risk jurisdictions | OR-15 | none | FATF-REF, FFIEC-APPF | WoWyrd rule available: A payment to or from a high-risk country high_risk_jurisdiction_counterparty |
| Cash withdrawn right after a credit arrives | OR-16 | Spending in the last 3 days doubles the monthly norm tp_u21_hist_deviation_3d_31d | FINCEN, FIU-UA | WoWyrd rule available: Cash taken out soon after money arrives cash_withdrawal_after_credit |
| The payee name does not match and the payment still goes | OR-17 | none | UK-PSR, EU-PSR | WoWyrd rule available: Paid although the payee name did not match payee_name_mismatch_paid |
| The payment reference mentions investment, crypto or a 'safe account' | OR-18 | none | UK-FINANCE | WoWyrd rule available: The payment reference uses common scam wording payment_reference_scam_wording |
| An older customer suddenly sends a large amount to a new payee | OR-19 | none | FINCEN | WoWyrd rule available: An older customer sends a large amount to a new payee older_customer_new_payee_large |
| Activity at hours unusual for the customer | OR-20 | none | NBU-DRAFT | WoWyrd rule available: Activity at an hour unusual for the customer unusual_hour_for_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
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: give it this folder with --previous.
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.
Checks are grouped by the regulator that sets the requirement. Each row gives the requirement ID, our own short wording of it, the result on your files, and the source's status on the date shown. Our wording is a summary, not the regulator's text.
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 ID | NBU draft paragraph | Our wording | Result | Finding | Evidence | Source status | As of | Official source |
|---|---|---|---|---|---|---|---|---|
| UA-NBU51-01 | — | 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 | Your transactions file has no payee-name or category-code column. Add them to the export so this can be measured. Without them no rule can check payment purpose against category code. | Transactions file: 58,331 rows; columns checked: payee_name, merchant_name, recipient_name, receiver_name, beneficiary_name, mcc, merchant_category_code. | in force since 20.05.2026; 6 months to comply (about 20.11.2026) | 2026-11-11 | bank.gov.ua |
| UA-NBU-01 | §66 | Review every rule at least monthly by back-testing it. (NBU draft §66; library item UA-NBU-01.) | Gap | The data covers 1 calendar month(s), 2022-09-01 to 2022-09-18. A monthly back-test needs one run per month; a trend needs 6 months. This run splits the data by day into 18 periods. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| UA-NBU-02 | §60 | Metric 1: compare how often each rule fired with how many payments were actually stopped. (NBU draft §60(1); library item UA-NBU-02.) | Partly met | Measured: 8.5%; no written threshold to compare against (§62). 11 rules fired 126,752 times; 10,835 of those hits were on stopped payments (8.5%). The per-rule table is in the technical report. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. First rules: Money from 5+ different senders into one account within 5 days (fan-in) 1,588 hits, 8 stopped; Many small payments in, then sent out within a day 15,845 hits, 1,974 stopped; Money sent to 5+ different recipients within 5 days (fan-out) 41,258 hits, 2,095 stopped; Single payment above 9,000 USD 12,042 hits, 2,008 stopped; Money in, then almost all of it sent on within 3 days (layering) 15,502 hits, 2,001 stopped; 10+ mid-size payments in 5 days, over 20,000 USD in total 1,771 hits, 102 stopped; 20+ small payments in 5 days, over 20,000 USD in total 349 hits, 24 stopped; Repeated payments just under 10,000 USD (structuring) 554 hits, 247 stopped; Transfer above 500 USD 36,685 hits, 2,114 stopped; More than 2 wire transfers in 7 days 653 hits, 125 stopped. | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| UA-NBU-03 | §60 | Metric 2: share of fraud value that was prevented, out of all fraud value. (NBU draft §60(2); library item UA-NBU-03.) | Partly met | Measured: under 0.1%; no written threshold to compare against (§62). Fraud value stopped: under 0.1% (246,596.74 of 1,398,433,325.74 USD). Fraud value with any alert: 100.0% (1,398,421,750.73 USD). Whether reviewed alerts were stopped is not in the decision log. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. 967 payments labelled fraud. | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| UA-NBU-04 | §62 | Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review. (NBU draft §62; library item UA-NBU-04.) | Gap | No written effectiveness threshold was given. As a pointer: 6 of 11 rules with at least 30 alerts with a known outcome catch fraud at or under the base fraud rate of 1.7%. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| UA-NBU-05 | §68–69 | Record a review decision for every rule: keep, adjust or cancel. (NBU draft §68–69; library item UA-NBU-05.) | Partly met | No recorded decisions in your files. Recommended decisions: cancel 6, adjust 0, keep 5. 0 rules have fewer than 30 alerts with a known outcome, so no decision is recommended. The decision itself is yours to record. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| UA-NBU-11 | — | Have evidence ready for a supervisor: documents, rules, risk markers. | Partly met | This report maps each finding to a requirement ID and its status (20 requirements). Your written rules, risk markers and staff interviews stay with you. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| UA-NBU51-02 | — | Show the acquirer's full name before an online payment; receipts show payee, commission, purpose and category code. | Not measurable from these files | No acquiring payment was found (operation_type purchase, or a card channel). This checks the data in your export, not your payment page or your receipts. Showing the acquirer's full name before an online payment stays a checklist question. | Transactions file, 58,331 rows. | in force since 20.05.2026; 6 months to comply (about 20.11.2026) | 2026-11-11 | bank.gov.ua |
| UA-NBU-09 | — | Reconcile payment operations every day. | Partly met | Days reviewed: 18 (2022-09-01 to 2022-09-18; UTC days). Days with no payments: 0. Payments with no row in the rule-hit log: 0. Rule-hit rows with no payment: 0. No ledger was given, so amounts were not reconciled. Give your settlement or ledger export with --ledger to reconcile them. This checks your exports. Whether your staff reconcile every day is a process question: answer it in the assessment checklist. | Transactions file and rule-hit log, by UTC day. | draft (NBU draft resolution on control of payment operations, published 2026-07-17; not law) | 2026-11-11 | bank.gov.ua |
| UA-NBU51-03 | — | Acquiring for natural persons only for allowed categories, with the required data passed to the issuer. | Not measurable from these files | Checklist question. The files do not show this. | Answer in the assessment checklist. | in force since 20.05.2026; 6 months to comply (about 20.11.2026) | 2026-11-11 | bank.gov.ua |
| UA-NBU54-01 | — | Non-bank providers that acquire payments need an authorisation; the sanctions pause has ended. | Not measurable from these files | Checklist question. The files do not show this. | Answer in the assessment checklist. | in force; grace period ended 02.09.2026 | 2026-11-11 | bank.gov.ua |
| UA-NBU116-01 | — | Remote verification of natural persons uses the updated procedure with credit-bureau data. | Not measurable from these files | Checklist question. The files do not show this. | Answer in the assessment checklist. | in force since 10.10.2026; 3 months to align internal procedures (about 10.01.2027) | 2026-11-11 | bank.gov.ua |
| UA-NBU116-02 | — | Reports to the State Financial Monitoring Service go only through the e-cabinet, with numbered registers. | Not measurable from these files | Checklist question. The files do not show this. | Answer in the assessment checklist. | in force since 10.10.2026; 3 months to align internal procedures (about 10.01.2027) | 2026-11-11 | bank.gov.ua |
| UA-16013-01 | — | Passing cards, account access or payment data to fraudsters becomes a crime. Detect and restrict accounts used as drops. | Not measurable from these files | Checklist question. The files do not show this. | Answer in the assessment checklist. | adopted by the Rada 28.10.2026; presidential signature not confirmed | 2026-11-11 | itd.rada.gov.ua |
Checks per EU requirements
| Requirement ID | Our wording | Result | Finding | Evidence | Source status | As of | Official source |
|---|---|---|---|---|---|---|---|
| EU-PSR-05 | 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 | Your transactions file has no payee name-check result. Add it to measure received transfers with a name mismatch or no check. | Columns looked for: name_check_result, payee_check_result, cop_result, vop_result, name_check. | agreed, not adopted (EU Payment Services Regulation; adoption expected by 12.2026) | 2026-11-11 | oeil.europarl.europa.eu |
Checks per UK requirements
| Requirement ID | Our wording | Result | Finding | Evidence | Source status | As of | Official source |
|---|---|---|---|---|---|---|---|
| UK-PSR-03 | A claim may carry an excess of up to 100 GBP, never for vulnerable customers. | Not measurable from these files | Checklist question. The files do not show this. | Answer in the assessment checklist. | in force | 2026-11-11 | psr.org.uk |
| UK-FCA-02 | Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice. | Partly met | 6 rules or thresholds look poorly calibrated on your data (retire 6); 4 catalogue rules never fired. Every proposal gives a plain-word reason. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. | 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 ID | Our wording | Result | Finding | Evidence | Source status | As of | Official source |
|---|---|---|---|---|---|---|---|
| US-NYDFS-01 | Analyse scenarios, rules and thresholds on an ongoing basis. | Partly met | This run analyses 11 rules over 18 periods by day (1 calendar month(s)). Ongoing analysis means running it every month. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. | in force | 2026-11-11 | dfs.ny.gov |
| US-NYDFS-02 | Test rules before and after they go live. | Not measurable from these files | The files do not show when each rule went live, so before-and-after tests cannot be checked. A replay of a new rule on past data can serve as the test before go-live. | Rule catalogue has no go-live date. | in force | 2026-11-11 | dfs.ny.gov |
| US-FFIEC-01 | Tune and validate monitoring; justify each threshold. | Partly met | 6 tuning proposals (retire 6). Each states its evidence on past data. | Source: your decision log and fraud labels, 2022-09-01 to 2022-09-18, labels known by 2022-09-18, label delay 7 days. | guidance | 2026-11-11 | bsaaml.ffiec.gov |
Other checks
No other checks in this run.
Run record
The files, code and parameters of this run, so it can be repeated.
| Item | Value | Source |
|---|---|---|
| Input file: catalogue | 1ba1a64a09faa99994d49f08f3234ed3049002776677a9c0bf586127f873e484 | SHA-256 |
| Input file: costs | 30f762bad066b62dfcb20d236f03995ea3edf0f809c04e934cdb957f3f4de2c4 | SHA-256 |
| Input file: decisions | 4f93135d000b15749c574990d5b6d621308ff9be94c4d041d7554e31c022430c | SHA-256 |
| Input file: labels | 5300406887cc1c2d31e72f5a5ae5e77ff197767e26a261670539900ccf30716c | SHA-256 |
| Input file: transactions | 85182da32f2e942304c498041a2eb2ba71989d5c6bc63d6f8737aa49b780d121 | SHA-256 |
| Collector version | v0.7.0-11-gba7bd7b03d5199dd42d1810a9e4294cde08c03a4 | git commit |
| Generation time | 2026-11-20 10:02 UTC | run time |
| cutoff | 2022-09-18T09:55:00+00:00 | client |
| label delay days | 7 | client |
| min cell | 10 | default |
| min join coverage | 0.95 | default |
| period | day | client |
| threshold | not given | not given |
| tokens for all rules | False | default |
| Regulatory library | 2026-11-11 | statuses as of this date |
| Requirement change file | not given | --changes |
| Tool map | b97e0d95e40f37467efa81e487c6763cfb06c7ff85447e629c887cfeebceed6f | SHA-256; tools.csv; 5 rows; 4 tools |
| Ledger export | not given | --ledger |
| Reference set source | built into this collector | |
| Reference set version | v0.7.0 | published 2026-11-18 |
| Reference set file | e96e792983d3748de554ba3b49a15291c8d4110f1778795555caff0fa81ee119 | SHA-256 |
Rule glossary
Each rule in this review, in plain words: what it detects, the fraud type it guards against, when it fires, where it comes from, and the data it needs.
10+ mid-size payments in 5 days, over 20,000 USD in total Rule ID: tp_u21_stats_10tx_1k3k_5d
- What it detects
- Finds a burst of many similar mid-size payments that add up to a large total.
- Fraud type it guards against
- Money laundering (many similar payments); structuring
- When it fires
- 10 or more payments in 5 days, each 1,000 to 3,000 USD on average, more than 20,000 USD in total.
- Source
- Unit21 open rule library
- Data fields it needs
- ts, sender_id, receiver_id, amount
20+ small payments in 5 days, over 20,000 USD in total Rule ID: tp_u21_stats_20tx_0_1k_5d
- What it detects
- Finds many small payments that together move a large sum.
- Fraud type it guards against
- Money laundering (smurfing); structuring
- When it fires
- 20 or more payments in 5 days, up to 1,000 USD each on average, more than 20,000 USD in total.
- Source
- Unit21 open rule library
- Data fields it needs
- ts, sender_id, receiver_id, amount
Dormant account suddenly moves more than 5,000 USD Rule ID: tp_u21_dormant_100d_5k
- What it detects
- Finds an account that was quiet for months and then starts moving money, as when a taken-over or sold account is put to use.
- Fraud type it guards against
- Account takeover; mule account
- When it fires
- No activity for more than 100 days, then more than 5,000 USD in or out within 5 days.
- Source
- Unit21 open rule library; the source gives no exact numbers, so WoWyrd chose some of them
- Data fields it needs
- ts, sender_id, receiver_id, amount
Large payment on an account less than 30 days old Rule ID: tp_ffiec_new_account_large_30d
- What it detects
- Finds big money movement on a newly opened account.
- Fraud type it guards against
- New-account fraud; mule account
- When it fires
- A payment of at least 10,000 USD where the sender or receiver account is 30 days old or less.
- Source
- FFIEC BSA/AML Examination Manual, Appendix F red flag; the source gives no exact numbers, so WoWyrd chose some of them
- Data fields it needs
- amount, account_age_days
Many small payments in, then sent out within a day Rule ID: tp_ffiec_small_in_rapid_out_24h
- What it detects
- Finds an account that collects several small payments and passes most of the money on at once.
- Fraud type it guards against
- Mule account; money laundering (pass-through)
- When it fires
- 3 or more incoming payments under 3,000 USD within 24 hours, then at least 80% of their total goes out within the same 24 hours.
- Source
- FFIEC BSA/AML Examination Manual, Appendix F red flag; the source gives no exact numbers, so WoWyrd chose some of them
- Data fields it needs
- ts, sender_id, receiver_id, amount
Money from 5+ different senders into one account within 5 days (fan-in) Rule ID: tp_ffiec_fan_in_5_senders_5d
- What it detects
- Finds one account that collects money from many people, as a collection or mule account does.
- Fraud type it guards against
- Mule account; scam proceeds collection
- When it fires
- One receiver gets money from 5 or more different senders within 5 days.
- Source
- FFIEC BSA/AML Examination Manual, Appendix F red flag; the source gives no exact numbers, so WoWyrd chose some of them
- Data fields it needs
- ts, sender_id, receiver_id
Money in, then almost all of it sent on within 3 days (layering) Rule ID: tp_u21_layering_10k_90pct_3d
- What it detects
- Finds an account that receives a large sum and quickly passes nearly all of it to other people.
- Fraud type it guards against
- Money laundering (layering); mule account
- When it fires
- At least 10,000 USD comes in, and at least 90% of it goes out to other receivers within 3 days.
- Source
- Unit21 open rule library
- Data fields it needs
- ts, sender_id, receiver_id, amount
Money sent to 5+ different recipients within 5 days (fan-out) Rule ID: tp_u21_fan_out_5_benef_5d
- What it detects
- Finds one sender spreading money to many receivers in a short time.
- Fraud type it guards against
- Money laundering (dispersal); mule network
- When it fires
- One sender pays 5 or more different receivers within 5 days.
- Source
- Unit21 open rule library
- Data fields it needs
- ts, sender_id, receiver_id
More than 2 wire transfers in 7 days Rule ID: tp_u21_wire_count_gt2_7d
- What it detects
- Finds a sender who uses wire transfers unusually often.
- Fraud type it guards against
- Money laundering through wires
- When it fires
- One sender makes more than 2 wire transfers within 7 days.
- Source
- Unit21 open rule library
- Data fields it needs
- ts, sender_id, channel
Repeated large round-number transfers Rule ID: tp_ffiec_round_amounts
- What it detects
- Finds a sender who keeps sending large, round amounts (a common money-laundering sign).
- Fraud type it guards against
- Money laundering; payments with no real purchase behind them
- When it fires
- One sender makes 3 or more transfers of at least 1,000 USD in whole hundreds within 30 days.
- Source
- FFIEC BSA/AML Examination Manual, Appendix F red flag; the source gives no exact numbers, so WoWyrd chose some of them
- Data fields it needs
- ts, sender_id, receiver_id, amount
Repeated payments just under 10,000 USD (structuring) Rule ID: tp_u21_structuring_9k_10k_5d
- What it detects
- Finds payments kept just below a reporting limit to avoid a report.
- Fraud type it guards against
- Structuring (avoiding the reporting threshold)
- When it fires
- One sender makes 2 or more payments between 9,000 and 10,000 USD within 5 days.
- Source
- Unit21 open rule library; the source gives no exact numbers, so WoWyrd chose some of them
- Data fields it needs
- ts, sender_id, receiver_id, amount
Single payment above 9,000 USD Rule ID: tp_u21_large_txn_9k
- What it detects
- Flags any one large payment for a closer look.
- Fraud type it guards against
- Large-value money laundering
- When it fires
- One payment is more than 9,000 USD.
- Source
- Unit21 open rule library
- Data fields it needs
- amount
Spending in the last 3 days doubles the monthly norm Rule ID: tp_u21_hist_deviation_3d_31d
- What it detects
- Finds a sender whose recent outgoing volume jumps far above their own usual level.
- Fraud type it guards against
- Account takeover; sudden cash-out
- When it fires
- The daily average sent over the last 3 days is more than twice the daily average over the last 31 days.
- Source
- Unit21 open rule library; the source gives no exact numbers, so WoWyrd chose some of them
- Data fields it needs
- ts, sender_id, receiver_id, amount
Transfer above 500 USD Rule ID: tp_u21_transfer_over_500
- What it detects
- Flags every transfer over a low fixed amount, so analysts see most mid-size transfers.
- Fraud type it guards against
- General transfer monitoring (no specific fraud type)
- When it fires
- One transfer is more than 500 USD.
- Source
- Unit21 open rule library
- Data fields it needs
- amount
Wire transfers above 4,999 USD in total within 7 days Rule ID: tp_u21_wire_total_gt4999_7d
- What it detects
- Finds a sender who moves a large total by wire in one week.
- Fraud type it guards against
- Money laundering through wires
- When it fires
- One sender's wire transfers add up to more than 4,999 USD within 7 days.
- Source
- Unit21 open rule library
- Data fields it needs
- ts, sender_id, amount, channel
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.