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

• Published in: arXiv.org
• Main Authors: Löw, Leander, Spindler, Martin, Brechmann, Eike
• Format: Paper
• Language: English
• 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

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...