IDS Case Study: Extracting Data from PDF and HTML Reports

By Keiter Technologies

IDS Case Study: Extracting Data from PDF and HTML Reports

Challenge and Opportunity

A client and large insurance company had hundreds of thousands of forms that underwriters had to manually read to approve applications. The name of the game in insurance is getting an accurate quote first. The insurance company needed a solution for more accurate and timely application processing.

Our Approach

  • Use Python to parse reports and extract required data.
  • Save all data to an Exasol database.
  • Maintain detailed entries on the several types of errors encountered.

Results

The system was able to parse 215,273 reports and found 57,529 valid issues within the reports in which the client was not aware. Aside from the automated QA, we are able to enhance/clean the data through NLP methods. This improved speed and accuracy of the previous method to underwrite these policies.

 

View All IDS Case Studies >

 

Learn More about our Innovative Data Solutions Services

 

Share this Insight:

About the Author


Keiter Technologies

Keiter Technologies

Keiter Technologies focuses on serving businesses with their strategic technology needs through data science, cybersecurity, and IT audit and consulting.

More Insights from Keiter Technologies

The information contained within this article is provided for informational purposes only and is current as of the date published. Online readers are advised not to act upon this information without seeking the service of a professional accountant, as this article is not a substitute for obtaining accounting, tax, or financial advice from a professional accountant.

Categories

Contact Us