Business Impact

  • ~85%

    Classification Accuracy

  • ~80%

    Extraction Accuracy

  • 7

    Types of Document Classified and 30+Fields Extracted

Customer Key Facts

  • Industry : Insurance
  • Country : United States
  • Size : 1000+ Employees

Problem Context

The customer is a top US insurer who wanted to automate the underwriting process for its New Business Applications, Childcare, and Worker Compensation Applications.


  • Time-consuming manual repetitive work
  • Long training time to onboard new document experts for re-ordering
  • No automated system to classify, extract and segregate documents


Quantiphi has deployed a sandbox that ingests the emails automatically and processes the attachments as required by the business. The solution performs the following functions:

Email ingestion: Real-time email ingestion system for ingesting attachments along with details of the sender, subject line, and timestamp

Document Classification: Classify documents based on the type and content of ACORD forms, loss runs, WC forms, CC forms, supplemental documents, or unknown

Extraction: Extract multiple fields and values from ACORD form 125, 126, 127, 130, 131, 140, Workers Compensation forms, and Child care forms

Transaction Definition: Based on the fields extracted from the documents, each submission is broken down into separate transactions

Output: The extracted output is then converted into IDX and XML formats to support the downstream applications


  • Industry leading classification and extraction accuracy for submission intake digitization
  • Extraction Support for handwritten scanned WC and CC forms
  • Streamlining and standardizing of underwriting workflows

Looking for similar project?

Let's Talk

Get your digital transformation started

Let's Talk