Use case 02
Recipient risk
Score the account being paid, not only the account paying.
- FIRST_TIME_RECIPIENT
- MULE_DORMANT_TO_EXPLOSIVE
- MULE_PASS_THROUGH
- MULE_RAPID_CASH_OUT
- MULE_SHARED_DEVICE
- MULE_UNRELATED_SENDERS
- RECIPIENT_FIRST_TIME_SENDER_CONCENTRATION
- RECIPIENT_MANY_SENDERS_1H
The problem
On instant and account-to-account rails the sending customer is often genuine. What distinguishes a scam payment from a normal one is the recipient: a new account collecting from a dozen first-time senders in an hour, forwarding within minutes.
How Cenvoriq approaches it
Recipient Risk is computed for the recipient of every transaction and reported with its own reason codes. It feeds Scam Risk when a large first payment goes to a recipient that already looks like a collector.
Status in the current release
Built and tested; shown in demo scenarios C and F.
- Receiving velocity and unique senders
- First-time-sender concentration
- Account age
- Rapid forwarding or cash-out after inflow
- Decayed shared signals from other cases
- Links to confirmed cases
Deployment
Measured in SHADOW before it touches a payment
A design partner replays its own tokenised history first, then mirrors a live stream. The engine scores this pattern and records the recommendation; the applied action is always allow and the institution’s own systems keep every control.