January 18, 2020

264 words 2 mins read

Real-time automated claim processing: The surprising utility of NLP methods on non-text data

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).

health automated algorithm dataset machine learning nlp
comments powered by Disqus
Executive Briefing: Best practices for human in the loopThe business case for active learning

Executive Briefing: Best practices for human in the loopThe business case for active learning

January 12, 2020

Deep learning works well when you have large labeled datasets, but not every team has those assets. Paco Nathan offers an overview of active learning, an ML variant that incorporates human-in-the-loop computing. Active learning focuses input from human experts, leveraging intelligence already in the system, and provides systematic ways to explore and exploit uncertainty in your data.
Scaling AI Inference Workloads with GPUs and Kubernetes

Scaling AI Inference Workloads with GPUs and Kubernetes

January 7, 2020

Deep Learning (DL) is a computational intense form of machine learning that has revolutionize many fields including computer vision, automated speech recognition, natural language processing and artif …
Tutorial: Kubeflow End-to-End: GitHub Issue Summarization

Tutorial: Kubeflow End-to-End: GitHub Issue Summarization

January 5, 2020

IMPORTANT NOTE:Due to the nature of tutorials, this session has been placed in a smaller capacity room to help facilitate a conducive learning environment. Space is very limited and seating will be g …
Improving DevOps and QA efficiency using machine learning and NLP methods

Improving DevOps and QA efficiency using machine learning and NLP methods

December 8, 2019

DevOps and QA engineers spend a significant amount of time investigating reoccurring issues. These issues are often represented by large configuration and log files, so the process of investigating whether two issues are duplicates can be a very tedious task. Ran Taig and Omer Sagi outline a solution that leverages NLP and machine learning algorithms to automatically identify duplicate issues.
Bladder cancer diagnosis using deep learning

Bladder cancer diagnosis using deep learning

November 28, 2019

Image recognition classification of diseases will minimize the possibility of medical mistakes, improve patient treatment, and speed up patient diagnosis. Mauro Damo and Wei Lin offer an overview of an approach to identify bladder cancer in patients using nonsupervised and supervised machine learning techniques on more than 5,000 magnetic resonance images from the Cancer Imaging Archive.
Improving user-merchant propensity modeling using neural collaborative filtering and wide and deep models on Spark BigDL at scale

Improving user-merchant propensity modeling using neural collaborative filtering and wide and deep models on Spark BigDL at scale

November 24, 2019

Sergey Ermolin and Suqiang Song demonstrate how to use Spark BigDL wide and deep and neural collaborative filtering (NCF) algorithms to predict a users probability of shopping at a particular offer merchant during a campaign period. Along the way, they compare the deep learning results with those obtained by MLlibs alternating least squares (ALS) approach.