From prediction to trust: enhancing deep learning models for insurance fraud detection through uncertainty quantification

This study applies uncertainty quantification techniques to deep neural networks for automobile insurance fraud detection to address the critical need for confidence estimation in artificial intelligence (AI)-driven decision systems. We evaluate three uncertainty quantification approaches: Monte Car...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Ziad Salem, Samer Sahl, Mohamed Hanafy Kotb Ibrahim
Format:	Artigo
Sprog:	Inglês
Udgivet:	PeerJ Inc. 2025-12-01
Serier:	PeerJ Computer Science
Fag:	Insurance fraud detection Deep learning Uncertainty quantification SHAP values Resampling
Online adgang:	https://peerj.com/articles/cs-3365.pdf
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!