Detect money laundering patterns in account activity

Banks, insurers and payment providers detect money laundering patterns in transactions

Needs setupAI Act: no extra obligationsFinding anomalies & fraudFinance

Fits: Legal & compliance · Finance & accounting

Monitoring finds structured deposits, rapid pass-through payments and turnover that does not match the customer profile, even when spread across many accounts and weeks. The anti-money laundering team reviews fewer false alarms from rigid individual rules and more cases that might really need a suspicious activity report.

Is this for you?

  • You have obligations under the Anti-Money Laundering Act (GwG), for example as a bank, payment institution or life insurer, and currently use rule-based monitoring whose alerts mostly turn out to be harmless.
  • Transaction data, customer profiles with expected turnover and the outcome of earlier reviews (harmless, suspicious activity report filed) are available in a form you can analyse.
  • The money laundering reporting officer, IT and data protection can jointly carry a project over several months.
First step today

Create a test table with about 20 made-up transactions across four accounts: two unremarkable ones, one with structured cash deposits followed by a transfer abroad, and one with many incoming payments that are forwarded immediately. Have it checked with the template below and see whether the reasons given are good enough for your anti-money laundering team to work with.

How to go about it

  1. Define typologies and risk factors
  2. Combine transactions, customer profiles and review outcomes
  3. Set up rules and a learning model
  4. Have alerts assessed by specialists
  5. Decide on reporting and consequences for the business relationship
  6. Adapt scenarios to new typologies

Templates to copy

Try it now
in the training
Analyse
in the training
Plan the rollout
in the training
Included in the training

The complete guide

  • 6 steps explaining exactly what to do
  • 3 proven templates to copy into your own AI
  • Safe use: data, checking, deciding, informing
  • Pitfalls, effort and how to recognise success

With the training you get all 430 guides for as long as your access runs.

See the trainingOne-off per person, no subscription

Same approach, other use cases

12 more use cases follow the pattern “Finding anomalies & fraud”.

Check claim notifications for signs of fraudCheck service charge statements for errorsDetect cheaters by their gameplay behaviourDetect market manipulation on trading platformsDetect phishing emails and suspicious sign-insDetect serial defects in fleet data before a recallFind duplicate and suspicious incoming invoicesIntercept fraudulent orders and card paymentsReview client bookkeeping for audit risks in advanceSelect tax cases for review on a risk basisStop fraudulent calls and SIM swap fraudTrack down electricity theft and tampered meters
‹ PreviousSee all use casesNext ›

G-FI-01 · Legal status 08.10.2026