Loan fraud
Detect devices behind fraudulent loan applications, from one device filing many under stolen or synthetic identities to bots submitting at scale.
Fingerprint fit Supporting signal
Overview
Loan application fraud happens when someone misrepresents or fabricates information to secure a loan they would not otherwise qualify for. It spans income falsification, stolen identities used to apply under a victim's name, and synthetic identities stitched together from real and fake details that match no single real person. Fraudsters often work at scale, buying personally identifiable information on darknet markets and using bots, proxies, and VPNs to submit applications across many lenders. A common pattern is one device or a small device farm cycling through many applications with different identity details, each made to look like a separate, distinct applicant. Bots add another layer, testing stolen credentials and authenticating victim accounts before opening loans or lines of credit.
Identity data alone is hard to trust, since synthetic and stolen identities are built to pass traditional checks, and verification steps like document upload or MFA add friction to a flow where lenders compete on speed. Fingerprint gives each browser and device a stable, unique Visitor ID that persists even when cookies are cleared, the IP changes, or the applicant identity changes, so a lender can recognize the same device behind multiple applications and tie a current session to past fraudulent activity. Smart Signals add the risk context around that identity: Bot Detection separates automated submissions and credential testing from real applicants, Proxy and VPN Detection surface attempts to hide location and evade IP checks, and on mobile the device-faking signals flag applications run from emulators, simulators, or cloned apps. Together these let a lender block, route to manual review, or step up only the risky cases.
Loan fraud primarily affects fintech and financial institutions: banks, credit card issuers, mortgage and auto lenders, payday and buy now pay later providers. The impact is direct monetary loss on defaulted fraudulent loans, plus distorted risk assessment that tightens credit markets and raises rates for legitimate borrowers, and long-term credit damage for the consumers whose identities are stolen. Mobile is an especially significant channel as more lending moves to apps.
How to implement it
-
Call Fingerprint when a loan application is submitted, before review. Store the Visitor ID with each application in your database and compare applications from one device.
-
Use Velocity Signals with linked ID to flag a burst of applications tied to one Visitor ID in a short window, a strong sign of automated submission or one fraudster working at scale.
-
Use Bot Detection to catch scripted loan applications and credential testing from bots, separating automated submissions from real applicants.
-
Use Proximity Detection to surface device farms, where many devices clustered in one location each submit an application that looks like a separate, distinct borrower.
-
Check Proxy and VPN Detection to catch applications submitted from rotating proxies or VPNs used to evade IP-based checks and conceal the applicant's real location.
-
Use Cloned App Detection on Android to flag duplicate app instances submitting many loan applications that appear to come from distinct borrowers.
-
On mobile, check Android Emulator and iOS Simulator Detection to catch high-volume application fraud run from emulated devices.
Which signals to check
Also known as
loan fraud · loan application fraud · loan application abuse · synthetic loan applications · fraudulent credit applications · credit application fraud · mortgage fraud · identity theft loan · synthetic identity fraud
Related use cases
-
Synthetic identity fraud
Catch fabricated identities, stitched together from real and fake personal data, by recognizing when many supposedly distinct applicants trace back to a single device or a cluster of co-located devices.
- Account Integrity
- Automation Risk
- +1
12 signals E-Commerce, Fintech, Gambling -
New account fraud
Detect fake or duplicate accounts created at scale for incentive abuse, ban evasion, spam, scalping, or rigging outcomes, even when the same device hides behind new emails and cleared cookies.
- Account Integrity
- Incentive Abuse
- +1
18 signals E-Commerce, Fintech, Gambling, Gaming, SaaS -
Fraud farms
Surface clusters of co-located devices that signal a device farm or organized fraud ring, even when each device looks unique on its own.
- Automation Risk
- Device Integrity
9 signals E-Commerce, Fintech, Gambling, Gaming