Premium
Insurance fraud detection with unsupervised deep learning
Author(s) -
Gomes Chamal,
Jin Zhuo,
Yang Hailiang
Publication year - 2021
Publication title -
journal of risk and insurance
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.055
H-Index - 63
eISSN - 1539-6975
pISSN - 0022-4367
DOI - 10.1111/jori.12359
Subject(s) - autoencoder , computer science , unsupervised learning , artificial intelligence , scope (computer science) , machine learning , deep learning , variable (mathematics) , artificial neural network , data science , mathematics , mathematical analysis , programming language
Abstract The objective of this paper is to propose a novel deep learning methodology to gain pragmatic insights into the behavior of an insured person using unsupervised variable importance. It lays the groundwork for understanding how insights can be gained into the fraudulent behavior of an insured person with minimum effort. Starting with a preliminary investigation of the limitations of the existing fraud detection models, we propose a new variable importance methodology incorporated with two prominent unsupervised deep learning models, namely, the autoencoder and the variational autoencoder. Each model's dynamics is discussed to inform the reader on how models can be adapted for fraud detection and how results can be perceived appropriately. Both qualitative and quantitative performance evaluations are conducted, although a greater emphasis is placed on qualitative evaluation. To broaden the scope of reference of fraud detection setting, various metrics are used in the qualitative evaluation.