CLIENT GOAL
This Case Study: Loan Document Processing discusses a leading national auto lender’s goal to streamline their processing and approval by organizing their loan packages into a consistent document sequence. Documents within loan packages were submitted by auto dealership partners in random order and the lender needed to separate the individual documents, classify the documents by type, and reorder the loan documents for delivery to their data processing and underwriting teams.
Axis Technical Groups’ goal was to allow them to quickly organize and prepare the loan documents in a repeatable fashion, resulting in time and cost savings over the manual handling of these complex documents.
BUSINESS CHALLENGE
The Client processes thousands of loan packages each month, where all the document types are combined and received as a single PDF. Their previous audit process required operators to manually work through these disorganized files that could contain the various document types in no particular order, often with document types missing pages or out of sequence.
This process of searching for documents within a loan package could take hours per individual loan. Additionally, these manually intensive tasks could not be leveraged by using lower-cost data entry clerks because compliance with loan underwriting standards required highly experienced users to identify and validate the correct information from the document.
DOCUMENT CLASSIFICATION
Axis’ sophisticated algorithms and use of Natural Language Processing (NLP) deliver high-quality results that are unmatched by any other platform.
Our solution automatically classifies, staples (virtually separates pages and builds document types back together), reorders and bookmarks the loan by the document type (i.e., income documents, utility bills, identification document like a driver’s license, etc.) into a consistent, easily digestible format, allowing underwriters to locate requisite information quickly and increase the speed of data entry.
Loan Document Processing involves an optical character recognition (OCR) process to convert the information into a computer-readable format, after which the OCR’d data and images are classified and analyzed using Natural Language Processing and Machine Learning technology.
The required documents are then returned in PDF format in a specific order to help streamline the data entered into the client’s loan origination system. Integration between the Axis solution and the client’s systems helps identify what the documents should look like and alerts the operator if any pages were missing from the package. The approval interface helps bring attention to potential errors and allows the user to quickly move through a loan package and only address exception handling.
DATA EXTRACTION
Following success with automating the document classification phase, the client used the Axis system to extract required data elements automatically and programmatically feed them to the Loan Origination System (LOS). Specific data elements such as driver’s license details are extracted, validated, and/or corrected, and the values are then returned to the client for ingestion into their business systems. This automation not only eliminates the vast majority of manual data entry but also allows lower-cost data entry clerks to validate the data. This frees up the underwriting SMEs and allows them to focus their primary purpose, which is to validate the loan and authorize the approval of the package. The combined savings in time and labor cost result in increased throughput, yielding improved loan customer service and tremendous savings per loan. Taking a conservative average of cost per loan multiplied by a number of loans brings the annual savings to potentially millions of dollars per year.
BOTTOM LINE
Axis offers a revolutionary product that delivers solutions that are faster, less expensive, and extend to a wider range of document processing challenges than ever before. No other vendor has the experience, technology, and know-how to address the most complex document processing opportunities.