Document Processing · Risk Management
BNP Paribas needed to reduce stress, delays, and manual errors in mortgage processing, where advisors had to enter, review, and verify large document files and the bank needed an average of 11 days to issue a digital offer.
Reported impact
The system shortens mortgage approval timelines, reduces manual work for advisors, improves file reliability, and helps BNP Paribas deliver a faster and simpler customer experience while strengthening risk checks.
BNP Paribas implemented an in-house AI-assisted mortgage processing workflow in November 2024 to accelerate basic home-loan approvals in France. The solution uses Intelligent Document Processing (IDP) built around the bank's internally developed Doc Factory software and NLP models trained on thousands of mortgage documents. Customer-submitted inputs such as purchase agreements, property tax documents, pay slips, and tax notices are ingested and parsed so the system can extract key fields and compare them with data already entered in the advisor's credit planning tool. The AI performs consistency checks across documents, validates borrower income details against supporting evidence, and checks the authenticity of tax notices. Results are surfaced directly inside the existing loan planning workflow, where IDP acts as a super assistant for advisors by automating document reading and validation rather than replacing human review.
Customers submit mortgage documents including purchase agreements, property tax records, pay slips, and tax notices. IDP and Doc Factory ingest the files, extract text and key fields with NLP models, validate them against borrower data already entered in the advisor's credit planning tool, and return matched or flagged results to advisors inside the existing mortgage workflow.
"It currently takes an average of 11 days to issue a digital offer."
"More than 80% of the document data is automatically read by AI and 60% of data is automatically matched and validated by AI."
"The AI has been trained on thousands of documents to identify the right data and then perform the appropriate checks."
"The end result is a significant time saving of around 30 minutes per file."
"The solution reads the documents provided by the customer and extracts the information needed to verify the contents of their property finance file."
"This AI was integrated directly into the existing loan planning tool"
"This IDP solution is already widely used within the Group and is based on NLP (Natural Language Processing) technologies."
"We use classic AI, which we have combined with an internally developed Intelligent Data Processing software called Doc Factory."
"since November 2024 we have implemented an artificial intelligence solution to streamline the entire process and shorten the loan approval time."
"the IDP therefore makes it possible to save 5 days and grant a mortgage in less than 30 days."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample May 12, 2026 Deutsche Bank Deutsche Bank needed to review third-party vendors' documentary evidence against its control framework and regulatory expectations faster without removing expert judgement, because onboarding and periodic reviews… A manual review would typically take around 30 minutes per evidence document. TPRM AI In-house Sample Oct 20, 2025 BNY BNY wanted to scale AI adoption across the company without fragmented point solutions, while maintaining strong governance, risk management, compliance controls, and practical support for workflows such as payments,… 75% more AI solutions in production compared to the prior quarter Contract Review Assistant · Eliza · Eliza agents In-house Sample May 26, 2025 BNP Paribas BNP Paribas must design and distribute investment products tailored to each retail customer while handling very large volumes of information, complying with stringent regulation, and giving advisers and customers clear… several billion possible combinations algorithm · automated preparation of performance reports · internal conversational assistants 