A Self-Attention Network for Hierarchical Data Structures with an Application to Claims Management

Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay out the non-fraudulent ones immediately. Modern machine lea...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Löw, Leander, Spindler, Martin, Brechmann, Eike
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 30.08.2018
Subjects
Artificial neural networks
Data structures
Fraud
Health care
Insurance
Machine learning
Neural networks
Structural hierarchy
Online AccessGet full text

Cover

More Information
Summary:Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay out the non-fraudulent ones immediately. Modern machine learning methods are well suited for this kind of problem. Health care claims often have a data structure that is hierarchical and of variable length. We propose one model based on piecewise feed forward neural networks (deep learning) and another model based on self-attention neural networks for the task of claim management. We show that the proposed methods outperform bag-of-words based models, hand designed features, and models based on convolutional neural networks, on a data set of two million health care claims. The proposed self-attention method performs the best.
ISSN:2331-8422