Fraud detection now included for every Ocrolus mortgage customer
TL;DR: Fraud detection is now included for every Ocrolus mortgage customer through Ocrolus Detect, Ocrolus’ document fraud detection product. Detect checks bank statements, pay stubs and tax forms for tampering, including documents that generative AI created or edited, and shows underwriters the results in the Ocrolus platform or the Encompass embedded viewer. JMAC Lending stopped nearly $2 million in fraudulent loan volume in its first months using Detect.
Fraud detection is now included for every Ocrolus mortgage customer through Ocrolus Detect, Ocrolus’ document fraud detection product. Detect checks bank statements, pay stubs and tax forms for tampering, and identifies documents that were altered or created with generative AI. Underwriters see the results in the Ocrolus platform or in the Encompass embedded viewer, where they already review the file. Ocrolus announced the news on Oct. 12 in Chicago.
The timing matters for mortgage lenders. Generative AI has made fake financial documents cheap and fast to produce, and across all lending types, 12% of loan applications processed through Ocrolus contain suspicious activity. For a mortgage lender, one altered document can bring a repurchase demand or a lost designation.
“The conversation with lenders has moved from ‘Can AI do this?’ to ‘Can I trust it enough to put it into production?'” said Nadia Aziz, General Manager of Mortgage at Ocrolus. “Fraudulent bank statements and income documents can now be created in minutes and are becoming harder to distinguish from the real thing. Fraud screening should be built in, not an added expense for lenders. Detect shows underwriters exactly why a document was flagged, and the underwriter makes the call.”
How Detect flags tampered and AI-generated documents
That trust starts with evidence. Through Ocrolus’ integration with Resistant AI, Detect now catches documents that generative AI created or edited, checking both what a document says and how it was made. Resistant AI’s forensic engine is trained on the threat patterns seen across more than 200 million global documents.
Each document gets an authenticity score with reason codes that show the underwriter what looks wrong. Examples include:
- Edited text
- Balances that don’t reconcile
- Changes made to the file after it was created
Because results appear in the Ocrolus platform or the Encompass embedded viewer, underwriters review Detect’s findings in the same place they already review the file. Every flag provides its reasoning, so the underwriter sees exactly why a document was flagged and makes the call.
Mortgage fraud detection in production: JMAC Lending stopped nearly $2 million in fraudulent loan volume in its first months of use.
Lenders are already running Detect in production. JMAC Lending, a wholesale lender based in Costa Mesa, California, screens every file in its Encompass pipeline with Detect.
JMAC stopped nearly $2 million in fraudulent loan volume in its first months of use. In one case, Detect led underwriters to a bank statement showing a $300,000 deposit in an account that held $1,200.
Before Detect, document authentication at JMAC came down to what a seasoned underwriter could catch on screen, according to the JMAC customer story. Now underwriters open the file, start with the flags, then work into the documents and authenticity scores behind them.
“We have zero tolerance for fraud,” said Dana Reminder, Director of Underwriting at JMAC Lending. “Ocrolus Detect is a partner to our underwriters to be their second set of eyes.”
Explainable results as AI governance requirements take effect
That transparency now carries regulatory weight. Freddie Mac’s and Fannie Mae’s AI governance requirements took effect earlier this year, and every Detect flag provides its reasoning, giving lenders an explainable result.
The same approach underpins Ocrolus’ integrations with Fannie Mae’s Income Calculator and Freddie Mac’s AIM Check.
Behind the product, Ocrolus maintains a formal AI governance program, with controls mapped to both frameworks to help meet the obligations they set out. The defined controls are audited annually by independent third parties (ISO 27001, SOC 2, PCI DSS) and through application security testing.
The people behind each rollout
Putting AI into production also takes people who know the work. Ocrolus’ in-house mortgage underwriting experts bring firsthand lending experience to product design and accuracy. They partner with account managers to support each rollout through onboarding, onsite training and ongoing adoption.
That combination is why lenders are trusting Ocrolus with more of the workflow. In the past 90 days, 40 lenders signed up for Ocrolus Inspect, which identifies data discrepancies and automates underwriting conditions.
To learn more about Ocrolus Detect and the Ocrolus mortgage suite, visit ocrolus.com.
Key takeaways
- Fraud detection is now included for every Ocrolus mortgage customer through Ocrolus Detect.
- Detect checks bank statements, pay stubs and tax forms for tampering, including documents that generative AI created or edited.
- Each document gets an authenticity score with reason codes, and results appear in the Ocrolus platform or the Encompass embedded viewer.
- JMAC Lending stopped nearly $2 million in fraudulent loan volume in its first months of using Detect.
- Every Detect flag provides its reasoning, giving lenders an explainable result as Freddie Mac’s and Fannie Mae’s AI governance requirements take effect.
FAQs
What is Ocrolus Detect?
Ocrolus Detect is Ocrolus’ document fraud detection product. It checks bank statements, pay stubs and tax forms for tampering, and it is now included for every Ocrolus mortgage customer.
How does Ocrolus Detect identify AI-generated documents?
Detect catches documents that generative AI created or edited. It checks both what a document says and how it was made.
What do Detect’s reason codes show underwriters?
Each document gets an authenticity score with reason codes that show the underwriter what looks wrong, such as edited text, balances that don’t reconcile or changes made to the file after it was created. The underwriter makes the call.
Where do underwriters see Detect results?
Underwriters see the results in the Ocrolus platform or in the Encompass embedded viewer, where they already review the file.
How does Detect relate to Fannie Mae and Freddie Mac AI governance requirements?
Freddie Mac’s and Fannie Mae’s AI governance requirements took effect earlier this year. Every Detect flag provides its reasoning, giving lenders an explainable result. Ocrolus maintains a formal AI governance program, with controls mapped to both frameworks to help meet the obligations they set out.
