Document processing time cut from 4 hours to 11 minutes per file
The Challenge
A mid-sized Hong Kong lender was processing 80–120 loan application files per day. Each file required a staff member to open, read, classify, extract key fields, and route to underwriting. The process took 3–4 minutes per page across an average 6-page file — consuming nearly 4 full-time hours of capacity daily.
What We Built
DeView built a document automation pipeline: inbound PDFs and scanned forms are processed through an extraction layer that classifies document type, pulls structured fields (applicant name, income figures, LTV ratios, employer details), and routes to the correct underwriting queue. Low-confidence outputs are flagged for human review; everything else moves automatically.
AI Capabilities
- 01
AI Document Classification
Inbound PDFs automatically classified by document type — application form, income verification, identity document, property valuation — and routed to the correct processing queue.
- 02
Structured Data Extraction
Key fields extracted from each document: applicant name, income figures, LTV ratios, employer details, and supporting document IDs. Output delivered as structured data ready for downstream systems.
- 03
Confidence-Based Routing
High-confidence extractions move automatically. Low-confidence items are flagged for human review with the specific field and reason highlighted — reviewers see context, not raw documents.
“We went from a backlog by 10am every day to same-day processing. The team now spends time on exceptions and client relationships — not reading PDFs.”
Head of Operations, mid-sized HK lender