Back

Ledgebrook AI-Powered Loss Run Extraction for Faster Decision-Making

Deveshi Dabbawala

February 24, 2025
Table of Content

Business Problem

  • Labor-Intensive Extraction: Underwriters had to manually extract claims history from variously formatted loss run documents, leading to inefficiencies. 
  • Data Inconsistencies: Unstructured data made it difficult to standardize extraction, leading to inaccurate risk assessments. 
  • Delayed Risk Analysis: Slow processing times hindered the ability to assess risk promptly and negotiate policy premiums effectively. 
  • Compliance Challenges: Inaccurate data extraction could result in non-compliance with industry regulations, impacting insurance decision-making.  

About Ledgebrook

Loss run documents contain crucial historical claims data required for risk assessment. Manually extracting this data was time-consuming and prone to errors. goML built an automated loss run extraction service to streamline this process. 

Solution

goML implemented a fully automated loss run data extraction pipeline: 

AI-Based Text Extraction: Leveraging AWS Textract, key claims data was extracted from unstructured PDFs and scanned documents.

Real-Time Search & Insights: Fast querying and retrieval of historical claims data for underwriting teams.

Lambda-Powered Data Processing: AWS Lambda functions processed the extracted data, standardizing it for structured storage.

Automation & Workflow Integration: The solution seamlessly integrated into Ledgebrook’s underwriting workflows, reducing dependency on manual processing. 

Centralized Data Repository: Extracted loss run data was stored in a PostgreSQL RDS database for easy retrieval and analysis.

AI-Powered Segregation & Classification: AWS Bedrock processed extracted text to segregate policies and claims. 

Architecture

  • User Interaction & API Triggers 
    POST /store-lossruns → Triggered inside the Document Service
    User uploads Loss Run Files, which are stored in AWS S3
  • Document Processing & Text Extraction 
    AWS Textract extracts: 
    Text details from the documents. 
    Tabular data and form structures as key-value pairs. 
  • AI-Powered Segregation & Classification 
    AWS Bedrock processes extracted text: 
    Segregation pipeline built to split text into multiple policies and claims
    Generates a Schema for Policies and Claims Segregation
  • Data Structuring & Storage 
    Bedrock extracts a Data Dictionary for every claim's text chunk. 
    Stores structured Loss Run responses in a database (presumably PostgreSQL or S3). 
  • Webhook Integration & Execution 
    Triggers a Webhook Endpoint once processing is completed. 
    Passes the structured Loss Run response to the Document Service for final execution. 
  • Data Retrieval & Response Generation 
    GET /loss-runs/{aiDocumentSessionToken} allows users to fetch the Loss Run Response
    Query retrieves stored Loss Run data from the database. 
    Returns structured response to the user. 

Outcomes

70%
Reduction in processing time
90%
Improvement in data accuracy
50%
Reduction in administrative costs