← All courses
$20

AI Financial-Crime Analyst

Build a bank-grade AML system: monitor transactions, resolve beneficial-ownership entity graphs, screen names against sanctions/PEP watchlists, detect money-laundering typologies, and ship an agent that triages each alert and drafts a Suspicious Activity Report — behind a human approval gate, with a full audit trail. Recall-first: catch every planted ring, then cut false positives.

"Surface the shell-company layering ring moving funds through three accounts — and draft the SAR"

6 Interactive Sessions

Short, interactive sessions: watch it work, try it, then build it yourself. You can go deeper at any time in the written chapters.

  1. 1

    Load the data, and lose nothing on the way

    Before you can spot money laundering, three files have to line up: what moved, who owns each account, and who you may not deal with. If a row goes missing between them, the crime can go missing with it.

  2. 2

    Find the one person behind many companies

    Work out which accounts, companies and spellings belong to the same real person, then map who really owns what.

  3. 3

    Check names against the sanctions list

    Catch every real match on the sanctions list first. Only then work on clearing the false alarms, and never in the other order.

  4. 4

    Spot laundering patterns, and tune in the right order

    Turn the patterns launderers really use into detectors, then make sure you catch every labelled case before you look at a single false alarm.

  5. 5

    An AI agent drafts the report, a person files it

    Let an AI agent do the gathering and the first draft, so analysts spend their time on judgement, and put a person in front of every filing.

  6. 6

    Run it day to day, and prove it works

    Give the pipeline a screen analysts can work from, watch the three numbers that show whether the program is healthy, and make every decision possible to reconstruct later.

Skills you'll practise

Data PipelineEntity ResolutionFuzzy ScreeningTypology DetectionHuman-in-the-Loop AgentAudit Trail

Practice data included

  • Transaction ledger (wire / ACH / card)
  • KYC customer & counterparty profiles
  • Sanctions / PEP watchlist
  • Labeled typology rings (structuring · layering)
  • Prior alerts & case history

How this certificate is scored

Your certificate shows how many of your written answers met the rubric below, checked by an AI grader. Anyone who checks your certificate sees it.

  • You answer 6 short questions, one for each module, in your own words (at least 40 words each).
  • An AI grader checks each answer against what its module asks for: it must answer the question, use the course's practice case specifically, and be correct.
  • To pass, at least 5 of the 6 answers must meet that bar. The certificate says the answers were graded by AI.

The rubric

  1. Module 1, Ingest: Transaction + entity + watchlist data model & loaders.
  2. Module 2, Resolve: Beneficial-ownership entity-resolution graph.
  3. Module 3, Screen: Sanctions/PEP fuzzy screening + customer risk scoring.
  4. Module 4, Detect: AML typology detectors + alert generation.
  5. Module 5, Triage Agent: Alert-triage agent that drafts a SAR (human-approved).
  6. Module 6, Deploy: Case-review UI + monitoring dashboard (FP rate, SLA).

What you walk away with

Shareable portfolio

A public URL showing your module timeline, patterns mastered, and completion status.

Everything you build

Download all your work as a ZIP file. It is yours to keep.

Module walkthrough

Each module documented with deliverables and the production pattern you implemented.

Ready to start AI Financial-Crime Analyst?

First course free. $20 per course after that.