Customer Story
How Arbor automates insurance compliance using Docsumo's smart data extraction APIs
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Best Document AI solution that comes with pre-trained APIs a CRE lender needs.
Howard Leiner
CTO, Arbor Realty Trust
About the customer
Arbor Realty Trust, Inc. is a real estate investment trust and direct lender, providing loan origination and servicing for multifamily, seniors housing, healthcare and other diverse commercial real estate assets all across the United States.
Industry
Commercial Real Estate
Company size
500+ Employees
Portfolio Units
10,000+ per Year
Document Processed
1 Bn+
The case study: In a nutshell
Before
Manually scanning Acord forms and flood certificates
A team of data entry operators spends hours manually extracting data from unstructured documents
Elevation certificates are highly unstructured that require more processing time than usual
Little to no validation done on captured data
All documents had to undergo double manual entry
After
Using intelligent document processing software to extract data
Employees review only exceptions
Certificates are now digitized with key data extracted from them
Docsumo's algorithms auto-classify documents and validate data with custom rules in real-time
95%+ straight through processing
The Challenge
Process large amounts of insurance documents
- Arbor receive insurance claim settlement and application documents in varying formats across different channels.
- A team of agents were stretched as they tried to manually capture data from these documents, and push for analysis.
Extract accurate data from Acord forms
- Arbor had to scan and extract accurate data from semi-structured Acord forms and elevation certificates
- Capturing data for a single application takes up to 30 minutes with a possible error rate of 20%.
Elevation certificates have varying structures
- Not only did the certificates vary for different vendors, but the field to capture often varies in term of position in the document.
- Some of them were in tabular formats.
No in-built validation procedures
- The manual extraction lacked a logical validation of captured data
The Docsumo Solution
Ingesting unstructured documents
- API-based direct integration that seamlessly ingests Acord 25, Acord 28, and Elevation certificates onto Docsumo.
Pre-processing and getting ready for data extraction
- Inbuilt document pre-processors identified the letter formats (JPG, PDF, PNG etc.) and queued them up for data extraction.
Data extraction from unstructured text
- Docsumo's OCR module used the vectorized position reference in a letter to extract data.
- The OCR not only parsed through letters with varying fonts, layouts, image quality, and resolution; it even extracted data from the tables with 95%+ accuracy.
Intelligent categorization of key value pairs
- Our proprietary NLP-based classification framework started rapidly learning from the debt settlement letter templates. It was trained to categorize key value pairs and line items.
- Another algorithm started making intelligent predictions to identify the data within a letter.
Rule-based data validation
- Once the data was extracted, a rule-based validation engine applied contextual data validation and correction algorithms.
Integration with downstream software
- The data was extracted in a JSON format that was easily integrated into downstream software for analysis
Result: 99%+ Data extraction accuracy
10x
Faster processing of unstructured data
95%
Touchless processing using smart validation rules
99%
Data accuracy with intelligent automation
Ready to automate your data extraction?
Let's talk.
Docsumo's intelligent document processing enables you to extract data easily, efficiently, and accurately.
Fill up the form to speak with an automation expert.
Fill up the form to speak with an automation expert.
