CCAR and DFAST Reporting Automation

As part of the Federal Reserve disclosure requirements driven by the Comprehensive Capital & Review (CCAR) and Dodd-Frank Act Stress Test (DFAST) regulations, certain financial institutions are expected to file a quantitative assessment of their portfolios as defined in the reporting form FR Y-14.  This assessment will involve the culling of significant data elements from the respective portfolios, which Paradatec’s advanced OCR solution can automate.

Specific to the mortgage market, our mortgage OCR library extracts the required data elements from the respective source documents, with the data provided in our standard XML format for easy consumption into the appropriate downstream processes.

  • With other OCR applications, the document content is expected and assumed to always appear in the same geographical areas on a document.  Our solution functions more like a human, reading all content regardless of location.
  • The process begins with a high-speed (sub-second) and efficient full-page OCR scan of each image.
  • This first step allows PROSAR-AIDA to search each and every word of every document and discover the content much as a human being would.
  • This overall process of discovery is unique, and makes PROSAR-AIDA very different from the typical structured or template-based solution.

FR Y-14M Compliance Support

Leverage our mortgage OCR solution to expedite the data gathering needed for your CCAR and DFAST compliance reporting

As a result of the CCAR regulations, CFOs of the largest US mortgage institutions must personally attest to the accuracy of data in their Loan Origination/Servicing systems relative to the documents of record in the original mortgage file.  This attestation clearly covers “Material weaknesses in internal controls or material errors or omissions in the data submitted”, with a risk of a charge of fraud for an incorrect attestation.

Paradatec’s mortgage OCR solution automatically reads mortgage documents and extracts the majority of data elements specified in Schedules A, B, and C of FR Y-14M.

  • In less than a second each page of the mortgage file is fully read and the relevant data fields are captured.
  • The end result is 75-80% of the work is completed more accurately than with human key entry and in a fraction of the time.
  • Extracted data is provided in XML format for easy manipulation to match your CCAR reporting standards.
  • Our solution is used for processing all correspondent loans in one of the largest CCAR banks, as well as a number of other large mortgage originators and servicers across the US.