Use case · Synthetic identity fraud · $0.2804 per applicant
Synthetic identity fraud
A real ID number.A borrowed face.A customer who is not real.
A synthetic identity is built from real pieces: a genuine ID number, someone else's photo, a fresh phone number. It passes simple checks, borrows, and disappears. Toden checks each piece against the others and against everyone you have already verified.
The workflow
Match the ID, the face and the record to each other, then search for the same face under another name. This is a starting point: add, remove or reorder any step in the workflow builder.
Step 01
$0.0714Document Intelligence
Reads the ID and checks it is genuine
Step 02
$0.069Government database validation
The number checked against the government record (Nigerian NIN shown)
Step 03
$0.06Passive Liveness
Confirms a live person
Step 04
$0.08Facial Match
Selfie against the photo on record
Step 05
IncludedFace Search
The same face under another name
Step 06
IncludedDecision rules
Approve, review or decline on your rules
Then your rules decide
A starting rule set
- The ID, the record and the face all agreeApprove
- The name differs from the government recordReview
- The same face is already a customer under another nameDecline
- The ID number is not on the government recordDecline
Every rule is yours to change on a visual canvas, and each result records which rule decided it. Publishing a new version needs no release.
Try the workflow builderWhat it costs
Added up from the published rate card as this page loaded. It is what one production run of the workflow above deducts from your credit.
$0.2804per applicant
- Document Intelligence$0.0714
- Government database validation · NIN$0.069
- Passive Liveness$0.06
- Facial Match$0.08
Connection map
When a face, a phone or an address turns up again, the console draws everyone gathered around it and says in plain words what the connection means and how much weight it deserves.
- Needs review2 people with this face verified under a different nameA shared address does not explain a shared face. Compare the photos before deciding.
- For context1 person with this face has the same name and documentThis may be a repeat verification. Check whether more than one account is expected.
- An illustration with invented people. In the console each card opens the customer's record.
How it works
Check the document and the record
The ID is read and its number is checked against the government record.
Match the live face
A liveness check confirms a real person, and the selfie is compared with the record's photo.
Search your own customers
The face is searched against everyone you have verified, to find the same person under another name.
What powers it
A real number with the wrong face fails, however good the document looks.
Integrate
Mount the SDK with the workflow you published, or send a hosted link and write no code. The result arrives by signed webhook, and changing the workflow never needs a release.
import { TodenVerification } from "@todenhq/sdk-react"; export function Verify({ userId }) { return ( <TodenVerification apiKey="pk_test_..." workflowId="wf_AbC123dEf456" userId={userId} onSubmit={(s) => save(s.verificationId)} /> );}{ "event": "verification.completed", "data": { "verificationId": "ver_8fk2...", "status": "verified", "assuranceLevel": "gov_db", "idType": "bvn", "country": "NG", "dataMatch": true, "facialMatch": true, "facialConfidence": 91 }}Products involved
This solution combines products you can use on their own too.
Related use cases
Coverage
Pick a country to see the IDs you can verify there, which documents carry a chip we read, and whether business checks are available.
Frequently asked
Nigeria, Ghana, Kenya, South Africa and Côte d'Ivoire. Elsewhere the document, the face and the face search still run.
Synthetic identity fraud,in one workflow.
The sandbox opens when you sign up. Usage-based pricing, no sales call.