Double work
one customer, two investigations
Two cases are opened against the same individual, and one team doesn't see the other.
By use case
Fraud and AML, one customer view
The fraud risk and the financial crime risk are both assessed using the same customer data and the same events, and both teams examine one record before reaching a decision.
What you switch on
Modules active for FRAML
By combining fraud indications with AML signals in the same customer record, teams can see the full risk picture rather than investigating each signal individually. All fraud indicators, screening results, transaction activity, and customer risk can be linked together in a single view.
Why this matters here
One customer, one platform, two teams, one view.
Fraud analysis doesn't consider list context, while AML analysis focuses on lists without considering behavior. The team responsible for one area deals with what the other team would have seen as a serious issue, and the discrepancy remains undetected until an examiner reviews the files.
Half the picture
signals kept apart
Behavior occurs without there being any list exposure. List exposure occurs without behavior.
Two records
two decisions
Escalation splits in two, and the audit trail splits with it
Single
risk score per customer
-44%
duplicated investigations
Different
disciplines, same record
100%
Signals traceable
Workflow · Two sides
Scroll to advance
One workflow, step by step
-
Step 01
One end-user, both data streams
Each transaction, event, and screening result links to one customer and is resolved.
-
Step 02
Score fraud and AML together
Velocity, along with device and network signals, considers PEP status, list exposure, and KYC context.
-
Step 03
Divergence triggers review
If the two viewpoints differ, the matter is referred to higher levels. No team handles the case alone.
-
Step 04
Shared case, full trail
The investigation into fraud and AML is carried out on the same record, and the export includes both views.
complead / fusion / entity
- Entities1,241,336
- Feeds attached2
- Conflicts flagged18
complead / fusion / score
- Behaviour signals9
- List signals3
- Fusion score82 review
complead / fusion / conflict
- Divergent cases18
- Escalated11
- Cleared with reason7
complead / cases / #4102
- Contributors2 teams
- Evidence items16
- Exportcombined
Entity
Score
Conflict
Case
What you answer to
What supervisors look for in a FRAML model
It's encouraged to combine fraud and AML. But a combined score that no one can explain isn't.
Read the compliance guides
Supervisor
Explainability of any combined score
Continuous
Regulator
Model governance and version history
Per change
Auditor
Decision log with contributing signals
Per case
FIU
Reporting unaffected by internal structure
On detection
Case study · Payments
Read the case study
Two teams stopped investigating the same person twice
Fraud and AML each ran their own queue on the same customer base. One shared entity record and one score removed the duplication and, more usefully, surfaced the cases where the two views disagreed.
−44%
Duplicated cases
18
Divergences found in month one
1
Shared queue
Cross-family links
Where teams like yours go next
FAQ
Before you ask us
What does FRAML mean on complead?
Fraud and AML risk assessed on the same customer data and the same events, so both teams work from one record. A mule account looks like unusual behavior to fraud and like layering to AML; FRAML means seeing both on the same customer at once.
Does a combined score hide the detail?
No. Each score breaks down into its contributing signals, their source and their weight. An investigator can see whether a high score came from device behaviour, list exposure or both, and an auditor can trace it the same way.
Do we need both fraud and AML modules?
Yes. Fusion needs at least two feeds. Most teams start with screening, which is already in place, and add fraud signals, since behaviour data is the missing half. A combined score built on one stream would not be combined.
Which signals go into the combined score?
Velocity, device and network signals, together with PEP status, list exposure and KYC context. Behavior without list context misses who the customer is, and list context without behavior misses what they are doing. The score reads both.
What happens when fraud and AML disagree?
The divergence itself triggers a review, so no team handles the case alone. A customer with clean lists and alarming behavior, or the reverse, is often exactly the case that falls between two teams.
Who owns a case that is both fraud and AML?
The team your escalation rules name. The other team contributes on the same record, so fraud and AML findings end up in one case with one trail, not two cases that reach different conclusions.
Will our auditor accept a combined model?
Auditors accept models they can interrogate. Model version, scoring basis, decision log and override path are all retained, so every combined score can be explained as it stood on the date it was produced. What supervisors reject is a score nobody can break down.
Does this stop two teams investigating the same customer?
Yes. One shared entity record means one case per customer instead of two, so the same mule is not investigated separately by fraud and AML in the same week. It also means one escalation and one audit trail.
Does a FRAML setup change our reporting obligations?
No. Reporting obligations stay the same whatever your team structure. The export carries both the fraud and AML views, with the signals, decisions and approvals from each, so the report reflects one consistent account of the case.
What do supervisors look for in a FRAML model?
Explainability of any combined score, model governance with full version history, and a decision log listing the contributing signals. Combining fraud and AML is welcome; a combined score that nobody can explain is not.
Find the cases your two teams disagree about
Send a month of fraud and AML outcomes on the same customers. The divergences are usually the interesting part.
3,000+
Data sources checked
220+
Countries covered
15 min
Always real-time data