Real-time automated claim processing: The surprising utility of NLP methods on non-text data
Processing claims is central to every insurance business. Amro Alkhatib shares a successful business case for automating claims processing, from idea to production. The machine learning-based claim automation model uses NLP methods on non-text data and allows auditable automated claims decisions to be made.
Talk Title | Real-time automated claim processing: The surprising utility of NLP methods on non-text data |
Speakers | Amro Alkhatib (National Health Insurance Company-Daman) |
Conference | Strata Data Conference |
Conf Tag | Make Data Work |
Location | New York, New York |
Date | September 11-13, 2018 |
URL | Talk Page |
Slides | Talk Slides |
Video | |
Daman is the largest health insurer in the United Arab Emirates. Since 2012, Daman has made important investments in people and technology to advance its analytical capabilities. With this analytical firepower and a historic dataset of 150 million claims, Daman was able to build and deploy a real-time ML-based claims processing engine that automates a significant portion of the manual claims processing workload, which could not be automated with simple medical rules. Amro Alkhatib explains how Daman repurposed existing NLP methods to search through tens of millions of historic claim decisions in real time, to find the most similar historical claims for a newly submitted claim. A new claim is then decided on via a transparent voting mechanism of decisions taken on similar historical claims. This approach allows machine learning algorithms to go into production in a highly regulated industry. Topics include: This project was a joint effort with a team of data scientists from Daman and D One Solutions, including Amro Alkhatib (Daman), Ruben Wolff (D One), and Asli Yaman (D one).