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

WoWyrd

WoWyrd · Rule review

Rule review: technical report

Client: Demo client with 3 business lines (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.

Totals

MeasureValue
Transactions58,331
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 hit928
Evaluable fraud (mature, not declined)948
False alarms50,302
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 transaction58,331 of 58,331 (100.0%)
Label rows that matched a transaction1,076 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.

RuleHitsNot yet matureDeclinedEvaluableCaughtFalse alarmsPrecisionRecall shareCost (USD)DecayedPrecision 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.
41,258202,09339,14521138,9340.5%22.3%95,904.24 USDNoPrecision per period for Money sent to 5+ different recipients within 5 days (fan-out) (Rule ID: tp_u21_fan_out_5_benef_5d)Values per period, first to last: 0%, 0%, 1%, 1%, 0%, 0%, 1%, 1%, 1%, 1%, 70%, no data, no data, 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.
36,6851412,11234,43283733,5952.4%88.3%77,428.24 USDNoPrecision per period for Transfer above 500 USD (Rule ID: tp_u21_transfer_over_500)Values per period, first to last: 1%, 1%, 5%, 5%, 3%, 3%, 2%, 3%, 2%, 6%, 76%, no data, no data, no data, no data, no data, no data, 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.
15,84501,97413,8716613,8050.5%7.0%23,994.16 USDNoPrecision per period for Many small payments in, then sent out within a day (Rule ID: tp_ffiec_small_in_rapid_out_24h)Values per period, first to last: 1%, 0%, 0%, 2%, 4%, 2%, 4%, 5%, 0%, 1%.
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.
15,502261,99913,47711913,3580.9%12.6%23,275.53 USDNoPrecision per period for Money in, then almost all of it sent on within 3 days (layering) (Rule ID: tp_u21_layering_10k_90pct_3d)Values per period, first to last: 1%, 0%, 1%, 1%, 0%, 5%, 3%, 5%, 1%, 1%, 67%, no data, no data, no data.
Single payment above 9,000 USD tp_u21_large_txn_9k
Flags any one large payment for a closer look.
12,042732,0069,9633459,6183.5%36.4%17,737.70 USDNoPrecision per period for Single payment above 9,000 USD (Rule ID: tp_u21_large_txn_9k)Values per period, first to last: 1%, 2%, 13%, 6%, 4%, 4%, 4%, 3%, 3%, 13%, 75%, no data, no data, no data, no data, no data, no data.
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.
1,5882771,5541001,4546.4%10.5%4,322.97 USDNoPrecision per period for Money from 5+ different senders into one account within 5 days (fan-in) (Rule ID: tp_ffiec_fan_in_5_senders_5d)Values per period, first to last: 2%, 4%, 14%, 12%, 9%, 12%, 7%, 5%, 4%, 5%, 100%, no data, no data, 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.
1,77131021,666311,6351.9%3.3%3,991.46 USDNoPrecision per period for 10+ mid-size payments in 5 days, over 20,000 USD in total (Rule ID: tp_u21_stats_10tx_1k3k_5d)Values per period, first to last: 4%, 1%, 6%, 4%, 2%, 2%, 2%, 1%, 0%, 4%, 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.
653012552805280.0%0.0%1,333.86 USDNoPrecision per period for More than 2 wire transfers in 7 days (Rule ID: tp_u21_wire_count_gt2_7d)Values per period, first to last: 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%.
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.
34912432423220.6%0.2%698.93 USDNoPrecision per period for 20+ small payments in 5 days, over 20,000 USD in total (Rule ID: tp_u21_stats_20tx_0_1k_5d)Values per period, first to last: 0%, 0%, 0%, 0%, 3%, 0%, 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.
505013736803680.0%0.0%625.00 USDNoPrecision per period for Wire transfers above 4,999 USD in total within 7 days (Rule ID: tp_u21_wire_total_gt4999_7d)Values per period, first to last: 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%, 0%.
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.
554124630773002.3%0.7%577.51 USDNoPrecision per period for Repeated payments just under 10,000 USD (structuring) (Rule ID: tp_u21_structuring_9k_10k_5d)Values per period, first to last: 0%, 0%, 0%, 0%, 2%, 4%, 4%, 0%, 7%, 0%, no data.

Hits and precision per period

Each cell: hits / precision in that period.

Rule2022-09-012022-09-022022-09-032022-09-042022-09-052022-09-062022-09-072022-09-082022-09-092022-09-102022-09-112022-09-122022-09-132022-09-142022-09-152022-09-162022-09-172022-09-18
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 data4 / no data7 / no data0 / no data0 / no data0 / no data0 / 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 data0 / no data0 / no data0 / no data0 / no data0 / no data0 / no data0 / 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 data3 / no data2 / no data0 / no data0 / no data0 / no data0 / 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 data15 / no data9 / no data1 / no data3 / no data4 / no data0 / 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 data6 / no data3 / no data0 / no data0 / no data0 / no data0 / 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 data3 / no data0 / no data0 / no data0 / no data0 / no data0 / no data0 / 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 data0 / no data0 / no data6 / 0.0%19 / 0.0%33 / 0.0%42 / 0.0%86 / 2.6%117 / 0.0%45 / 0.0%1 / no data0 / no data0 / no data0 / no data0 / no data0 / no data0 / no data0 / 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 data0 / no data1 / no data0 / no data0 / no data0 / no data0 / no data0 / 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 data29 / no data18 / no data3 / no data3 / no data5 / no data1 / 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 data0 / no data0 / no data0 / no data0 / no data0 / no data0 / no data0 / 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 data0 / no data0 / no data0 / no data0 / no data0 / no data0 / no data0 / 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

Rule ARule BJaccardTransactions hit by both
Money sent to 5+ different recipients within 5 days (fan-out) tp_u21_fan_out_5_benef_5dTransfer above 500 USD tp_u21_transfer_over_5000.4925,731
More than 2 wire transfers in 7 days tp_u21_wire_count_gt2_7dWire transfers above 4,999 USD in total within 7 days tp_u21_wire_total_gt4999_7d0.49382
Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24hMoney in, then almost all of it sent on within 3 days (layering) tp_u21_layering_10k_90pct_3d0.388,706
Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24hMoney sent to 5+ different recipients within 5 days (fan-out) tp_u21_fan_out_5_benef_5d0.3514,842
Money sent to 5+ different recipients within 5 days (fan-out) tp_u21_fan_out_5_benef_5dMoney in, then almost all of it sent on within 3 days (layering) tp_u21_layering_10k_90pct_3d0.3414,408
Single payment above 9,000 USD tp_u21_large_txn_9kTransfer above 500 USD tp_u21_transfer_over_5000.3312,042
Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24hTransfer above 500 USD tp_u21_transfer_over_5000.2510,367
Money in, then almost all of it sent on within 3 days (layering) tp_u21_layering_10k_90pct_3dTransfer above 500 USD tp_u21_transfer_over_5000.249,949
Money sent to 5+ different recipients within 5 days (fan-out) tp_u21_fan_out_5_benef_5dSingle payment above 9,000 USD tp_u21_large_txn_9k0.188,170
Single payment above 9,000 USD tp_u21_large_txn_9kMoney in, then almost all of it sent on within 3 days (layering) tp_u21_layering_10k_90pct_3d0.143,470
Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24hSingle payment above 9,000 USD tp_u21_large_txn_9k0.143,478
Single payment above 9,000 USD tp_u21_large_txn_9kRepeated payments just under 10,000 USD (structuring) tp_u21_structuring_9k_10k_5d0.05554
Money from 5+ different senders into one account within 5 days (fan-in) tp_ffiec_fan_in_5_senders_5dTransfer above 500 USD tp_u21_transfer_over_5000.031,131
10+ mid-size payments in 5 days, over 20,000 USD in total tp_u21_stats_10tx_1k3k_5dTransfer above 500 USD tp_u21_transfer_over_5000.031,025
Repeated payments just under 10,000 USD (structuring) tp_u21_structuring_9k_10k_5dWire transfers above 4,999 USD in total within 7 days tp_u21_wire_total_gt4999_7d0.0225

Rules that never fired

RuleInput fieldsStatus
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_daysInput 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, amountInput 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, amountInput 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, amountInput 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-80e229b9. Quote this reference in your change record.

Retire the ruleConfidence: mediumPriority: 62.17

Rules

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.
Sources:
  • 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-0ee48cf1. Quote this reference in your change record.

Retire the ruleConfidence: highPriority: 60.08

Rules

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.
Sources:
  • 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-2266ce85. Quote this reference in your change record.

Retire the ruleConfidence: highPriority: 60.02

Rules

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.
Sources:
  • 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-2a81ffc0. Quote this reference in your change record.

Retire the ruleConfidence: mediumPriority: 60.01

Rules

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.
Sources:
  • 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-fdf9b021. Quote this reference in your change record.

Retire the ruleConfidence: highPriority: 60.0

Rules

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.
Sources:
  • 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-2fed05c6. Quote this reference in your change record.

Retire the ruleConfidence: mediumPriority: 59.97

Rules

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.
Sources:
  • 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-470735c7. 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.
Sources:
  • 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-409090ac. 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.
Sources:
  • 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-0e811d6e. 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.
Sources:
  • 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-6448ec99. 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.
Sources:
  • 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-34bfe5f0. 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.
Sources:
  • 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-f5b6e1f7. 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.
Sources:
  • UK-FINANCE
  • UK-PSR

Add a rule for: A new merchant's volume is far above similar merchants, then the merchant closes

Reference REC-a414e3b2. 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.
Sources:
  • 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-b5cac26a. 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.
Sources:
  • NBU-DRAFT

Add a rule for: An older customer suddenly sends a large amount to a new payee

Reference REC-691bf0b5. 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.
Sources:
  • FINCEN

Add a rule for: Contacts, device, apps, IMEI, operating system or network address change often

Reference REC-bde66de3. 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.
Sources:
  • 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-f4e5fd37. 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.
Sources:
  • FIU-UA
  • FINCEN

Add a rule for: Many senders' accounts share one beneficiary

Reference REC-82a0c21e. 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.
Sources:
  • WOWYRD-SPIKE
  • FINCEN

Add a rule for: Merchant account inflows mirror its outflows (transit)

Reference REC-af567191. 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.
Sources:
  • UA-NBU-S10 (Merchant account inflows mirror its outflows (transit))

Add a rule for: One device fingerprint is used by unrelated users

Reference REC-2392187c. 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.
Sources:
  • 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-b7c65d36. 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.
Sources:
  • 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-baa88b73. 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.
Sources:
  • UK-PSR
  • EU-PSR

Add a rule for: The payment reference mentions investment, crypto or a 'safe account'

Reference REC-eebacaab. 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.
Sources:
  • UK-FINANCE

Add a rule for: Transfers to or from high-risk jurisdictions

Reference REC-0d627694. 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.
Sources:
  • FATF-REF
  • FFIEC-APPF

Add a rule for: Two operations are too far apart to travel between in the time

Reference REC-3d1fe0d0. 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.
Sources:
  • UA-NBU-S14 (Two operations are too far apart to travel between in the time)

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 types present in your labelsSpread, then collect: 97 caught, 1 missed; Layers of accounts: 83 caught, 3 missed; Collect, then spread: 83 caught, 1 missed; One out to many (fan-out): 83 caught, 0 missed; Many into one (fan-in): 52 caught, 2 missed; Two groups paying each other: 47 caught, 2 missed; Money in a circle: 43 caught, 1 missed; Random hops: 40 caught, 1 missed; Type not given: 400 caught, 28 missedSpread, then collectSpread, then collectSpread, then collect: 97 caughtSpread, then collect: 1 missed97 caught, 1 missedLayers of accountsLayers of accountsLayers of accounts: 83 caughtLayers of accounts: 3 missed83 caught, 3 missedCollect, then spreadCollect, then spreadCollect, then spread: 83 caughtCollect, then spread: 1 missed83 caught, 1 missedOne out to many (fan-out)One out to many (fan-out)One out to many (fan-out): 83 caught83 caught, 0 missedMany into one (fan-in)Many into one (fan-in)Many into one (fan-in): 52 caughtMany into one (fan-in): 2 missed52 caught, 2 missedTwo groups paying each otherTwo groups paying each otherTwo groups paying each other: 47 caughtTwo groups paying each other: 2 missed47 caught, 2 missedMoney in a circleMoney in a circleMoney in a circle: 43 caughtMoney in a circle: 1 missed43 caught, 1 missedRandom hopsRandom hopsRandom hops: 40 caughtRandom hops: 1 missed40 caught, 1 missedType not givenType not givenType not given: 400 caughtType not given: 28 missed400 caught, 28 missed
Labelled fraud cases per type. Blue: a rule fired on the payment. Orange: no rule fired. Source: labels file and rule-hit log, labels known by the cut-off.
Fraud typeLabelled casesCaughtMissedLibrary types it matchesYour rules' coverageWoWyrd
Spread, then collect98971Money comes in and leaves fast, little balance stays (UA-NBU-S06), Most of an incoming amount leaves again within hours (OR-02)CoveredWoWyrd rule available: Money leaves soon after it arrives rapid_pass_through
Layers of accounts86833noneCoveredWoWyrd rule: planned
Collect, then spread84831Money 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)CoveredWoWyrd 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)83830One payer sends to far more payees than similar payers (UA-NBU-S15), One account pays many new beneficiaries (OR-07)CoveredWoWyrd rule available: One account pays many different payees account_many_payees
Many into one (fan-in)54522Many 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)CoveredWoWyrd rule available: Many senders pay one account inbound_sender_fan_in; One payee shared by several customers beneficiary_reuse
Two groups paying each other49472noneCoveredWoWyrd rule: planned
Money in a circle44431Money goes round in a circle between accounts within days (OR-11)CoveredWoWyrd rule: planned
Random hops41401noneCoveredWoWyrd rule: planned
Type not given42840028noneUnknownWoWyrd 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 typeIDYour rules whose names matchSourcesWoWyrd
One user holds many more accounts or cards than similar usersUA-NBU-S01noneUA-NBU-S01WoWyrd rule: planned
One type of operation makes up an unusual share of a user's activityUA-NBU-S02noneUA-NBU-S02WoWyrd rule available: One type of operation dominates an account operation_type_concentration
Many operations of one type in a short time, incoming or outgoingUA-NBU-S03Money from 5+ different senders into one account within 5 days (fan-in) tp_ffiec_fan_in_5_senders_5dUA-NBU-S03WoWyrd 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 throughUA-NBU-S04Many small payments in, then sent out within a day tp_ffiec_small_in_rapid_out_24hUA-NBU-S04WoWyrd 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 againUA-NBU-S05noneUA-NBU-S05WoWyrd rule available: Large loans taken and repaid again and again loan_issue_repayment_churn
Gambling winnings arrive with no deposits, then card transfers followUA-NBU-S07noneUA-NBU-S07WoWyrd rule available: Gambling winnings with no gambling deposits gambling_winnings_without_deposits
Regular transfers to a personal account look like business activityUA-NBU-S08noneUA-NBU-S08WoWyrd 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 closesUA-NBU-S09noneUA-NBU-S09WoWyrd rule available: A merchant with little history suddenly busy low_history_merchant_spike
Merchant account inflows mirror its outflows (transit)UA-NBU-S10noneUA-NBU-S10WoWyrd rule available: A business account pays out almost all it receives business_account_transit
Payment purposes do not fit the merchant's category codeUA-NBU-S11noneUA-NBU-S11WoWyrd 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 oftenUA-NBU-S12noneUA-NBU-S12WoWyrd 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 usersUA-NBU-S13noneUA-NBU-S13WoWyrd rule available: One device used by several customers multi_account_device
Two operations are too far apart to travel between in the timeUA-NBU-S14noneUA-NBU-S14WoWyrd rule available: Locations too far apart for the time between them impossible_travel
A new account gets large or many credits soon after openingOR-03Large payment on an account less than 30 days old tp_ffiec_new_account_large_30dUNIT21, UK-FINANCEWoWyrd 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 amountsOR-04Dormant account suddenly moves more than 5,000 USD tp_u21_dormant_100d_5kFFIEC-APPFWoWyrd rule: planned
Repeated amounts just under a reporting or limit thresholdOR-0510+ 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_5dFFIEC-APPFWoWyrd 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 reasonOR-06Repeated large round-number transfers tp_ffiec_round_amountsFFIEC-APPFWoWyrd rule available: Several payments in large round amounts repeated_round_amounts
Outgoing payments per hour above the customer's usual levelOR-08Spending in the last 3 days doubles the monthly norm tp_u21_hist_deviation_3d_31dUNIT21, EBA-GL-2021-02WoWyrd 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 beforeOR-09noneUK-FINANCE, UK-PSRWoWyrd rule available: A large payment to a payee added just before new_payee_high_amount
Many senders' accounts share one beneficiaryOR-10noneWOWYRD-SPIKE, FINCENWoWyrd rule available: One payee shared by several customers beneficiary_reuse
An amount far above the customer's own historyOR-12Spending in the last 3 days doubles the monthly norm tp_u21_hist_deviation_3d_31dEBA-GL-2021-02, NBU-DRAFTWoWyrd rule available: A payment far above the customer's usual amount amount_far_above_customer_average
Credits from many different banks into one accountOR-14noneFIU-UA, FINCENWoWyrd rule available: Credits from many different banks into one account inbound_from_many_banks
Transfers to or from high-risk jurisdictionsOR-15noneFATF-REF, FFIEC-APPFWoWyrd rule available: A payment to or from a high-risk country high_risk_jurisdiction_counterparty
Cash withdrawn right after a credit arrivesOR-16Spending in the last 3 days doubles the monthly norm tp_u21_hist_deviation_3d_31dFINCEN, FIU-UAWoWyrd rule available: Cash taken out soon after money arrives cash_withdrawal_after_credit
The payee name does not match and the payment still goesOR-17noneUK-PSR, EU-PSRWoWyrd 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-18noneUK-FINANCEWoWyrd rule available: The payment reference uses common scam wording payment_reference_scam_wording
An older customer suddenly sends a large amount to a new payeeOR-19noneFINCENWoWyrd rule available: An older customer sends a large amount to a new payee older_customer_new_payee_large
Activity at hours unusual for the customerOR-20noneNBU-DRAFTWoWyrd 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 IDNBU draft paragraphOur wordingResultFindingEvidenceSource statusAs ofOfficial 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 filesYour 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)2026-11-11bank.gov.ua
UA-NBU-01§66Review every rule at least monthly by back-testing it. (NBU draft §66; library item UA-NBU-01.)GapThe 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)2026-11-11bank.gov.ua
UA-NBU-02§60Metric 1: compare how often each rule fired with how many payments were actually stopped. (NBU draft §60(1); library item UA-NBU-02.)Partly metMeasured: 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)2026-11-11bank.gov.ua
UA-NBU-03§60Metric 2: share of fraud value that was prevented, out of all fraud value. (NBU draft §60(2); library item UA-NBU-03.)Partly metMeasured: 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)2026-11-11bank.gov.ua
UA-NBU-04§62Set rule-effectiveness thresholds in writing. A rule under its threshold gets an immediate review. (NBU draft §62; library item UA-NBU-04.)GapNo 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)2026-11-11bank.gov.ua
UA-NBU-05§68–69Record a review decision for every rule: keep, adjust or cancel. (NBU draft §68–69; library item UA-NBU-05.)Partly metNo 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)2026-11-11bank.gov.ua
UA-NBU-11—Have evidence ready for a supervisor: documents, rules, risk markers.Partly metThis 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)2026-11-11bank.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 filesNo 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)2026-11-11bank.gov.ua
UA-NBU-09—Reconcile payment operations every day.Partly metDays 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)2026-11-11bank.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 filesChecklist 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)2026-11-11bank.gov.ua
UA-NBU54-01—Non-bank providers that acquire payments need an authorisation; the sanctions pause has ended.Not measurable from these filesChecklist question. The files do not show this.Answer in the assessment checklist.in force; grace period ended 02.09.20262026-11-11bank.gov.ua
UA-NBU116-01—Remote verification of natural persons uses the updated procedure with credit-bureau data.Not measurable from these filesChecklist 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)2026-11-11bank.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 filesChecklist 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)2026-11-11bank.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 filesChecklist question. The files do not show this.Answer in the assessment checklist.adopted by the Rada 28.10.2026; presidential signature not confirmed2026-11-11itd.rada.gov.ua

Checks per EU requirements

Requirement IDOur wordingResultFindingEvidenceSource statusAs ofOfficial source
EU-PSR-05When 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 filesYour 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)2026-11-11oeil.europarl.europa.eu

Checks per UK requirements

Requirement IDOur wordingResultFindingEvidenceSource statusAs ofOfficial source
UK-PSR-03A claim may carry an excess of up to 100 GBP, never for vulnerable customers.Not measurable from these filesChecklist question. The files do not show this.Answer in the assessment checklist.in force2026-11-11psr.org.uk
UK-FCA-02Test and review rules; a poorly calibrated rule set the firm cannot explain is poor practice.Partly met6 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 force2026-11-11fca.org.uk

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

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

Requirement IDOur wordingResultFindingEvidenceSource statusAs ofOfficial source
US-NYDFS-01Analyse scenarios, rules and thresholds on an ongoing basis.Partly metThis 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 force2026-11-11dfs.ny.gov
US-NYDFS-02Test rules before and after they go live.Not measurable from these filesThe 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 force2026-11-11dfs.ny.gov
US-FFIEC-01Tune and validate monitoring; justify each threshold.Partly met6 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.guidance2026-11-11bsaaml.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.

ItemValueSource
Input file: catalogue1ba1a64a09faa99994d49f08f3234ed3049002776677a9c0bf586127f873e484SHA-256
Input file: costs30f762bad066b62dfcb20d236f03995ea3edf0f809c04e934cdb957f3f4de2c4SHA-256
Input file: decisions4f93135d000b15749c574990d5b6d621308ff9be94c4d041d7554e31c022430cSHA-256
Input file: labels5300406887cc1c2d31e72f5a5ae5e77ff197767e26a261670539900ccf30716cSHA-256
Input file: transactions85182da32f2e942304c498041a2eb2ba71989d5c6bc63d6f8737aa49b780d121SHA-256
Collector versionv0.7.0-11-gba7bd7b03d5199dd42d1810a9e4294cde08c03a4git commit
Generation time2026-11-20 10:02 UTCrun time
cutoff2022-09-18T09:55:00+00:00client
label delay days7client
min cell10default
min join coverage0.95default
perioddayclient
thresholdnot givennot given
tokens for all rulesFalsedefault
Regulatory library2026-11-11statuses as of this date
Requirement change filenot given--changes
Tool mapnot given--tools or a tool column in the catalogue
Ledger exportnot given--ledger
Reference set sourcebuilt into this collector
Reference set versionv0.7.0published 2026-11-18
Reference set filee96e792983d3748de554ba3b49a15291c8d4110f1778795555caff0fa81ee119SHA-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.