Skip to content

Fraud prevention for lenders and NBFCs

You decide in minutes and see the loss months later. The applications that default first share a face, a device or a payout account with another, and nothing at the desk shows it.

Journey most at risk
Application and disbursal
Who signs off
Chief risk officer, Head of credit risk, Head of onboarding
The decisionS-6823

Block

BLOCK · face reused · emulator · scripted timing · payout account shared
Your customer sees
We can’t continue with this application in the app. If you think this is a mistake, contact us and we’ll look at it with you.
Your FRM receives
FACE_REUSEDEMULATORSCRIPTED_TIMINGACCOUNT_SHARED
Stopped or heldIllustrative
The decision on the journey most at risk here, from the loan stacking use case. Real codes are agreed in the sandbox.

What lenders face now.

  • Generated documents and faces build applicants who pass KYC.
  • The same person, phone or face applies at many lenders within days, and the bureau has not caught up.
  • Losses arrive months later, as first-payment default.

Across the customer journey.

Where each attack appears for lenders, what DeepID reads at that moment and the action it returns. Each moment is checked against what the one before it bound.

MomentThe attackWhat DeepID doesDecision
ApplicationStacked applications and synthetic identitiesA face already seen under another name, many applications on one device, and a form filled by a script.Cool off or block
VerificationEdited documents and borrowed identitieseKYC and the document checked at the source, the live face matched to the portrait and searched across your applicants.Step up
DisbursalPayout to a mule or a ring accountThe payout account verified against the name on it and scored against the mule graph before the money leaves.Hold
ServicingAccount handover and collection fraudA change of device or behaviour after disbursal, and a repayment account change read as a new-phone event.Step up, then cool off

Where to start.

The journey most at risk: application and disbursal. Start at application, where eKYC, the document and the live face are checked at the source and the phone is bound, so that disbursal has something to check against.

  1. 1Sign-upeKYC, the document and a live face, bound to the phone.
  2. 2Loan stackingThe synthetic ring, and the cool-off or block before disbursal.
  3. 3Video KYC deepfakesThe video KYC call, with the camera read below the picture.
  4. 4Assisted channel fraudThe customer confirms on her own phone before an assisted action.

Your free first analysis.

A free retrospective on 30 to 90 days of applications, disbursals and early repayment.

What it shows. The defaulted loans that shared a face, device or payout account with another application, and whether that link was visible before disbursal. No figure is published for this; you count it on your own data, against what you see today.

How the retrospective works

Use cases for lenders.

Each shows how the attack unfolds, what your checks saw at each step, what DeepID read and the decision it returned.

  • Loan stacking

    Catch stacked and synthetic applications before disbursal.Cool off or block
  • Video KYC deepfakes

    A live person, in front of a real camera, on every video KYC call.Step up, hold or block
  • Assisted channels

    Prove the customer is there, on her own phone, before an assisted action.Step up, or hold
  • Account takeover

    Protect the account through recovery and the hours after.Step up, then cool off
  • Insider fraud

    Hold the takeover that starts with a contact change made from the inside.Step up, then hold

Rules that apply.

India first. Each rule is dated and sourced on its market page, and the rule map covers the six other markets.

India’s rules

The rule map, by market

DeepID supports compliance with these rules. It never claims to guarantee it.

See DeepID on a real phone.

We show your fraud, security and engineering leads how DeepID would run your sign-up, login or payment journey, then plan a pilot on your own traffic.