The University of Southampton
University of Southampton Institutional Repository

Social network analytics for supervised fraud detection in insurance

Social network analytics for supervised fraud detection in insurance
Social network analytics for supervised fraud detection in insurance

Insurance fraud occurs when policyholders file claims that are exaggerated or based on intentional damages. This contribution develops a fraud detection strategy by extracting insightful information from the social network of a claim. First, we construct a network by linking claims with all their involved parties, including the policyholders, brokers, experts, and garages. Next, we establish fraud as a social phenomenon in the network and use the BiRank algorithm with a fraud-specific query vector to compute a fraud score for each claim. From the network, we extract features related to the fraud scores as well as the claims' neighborhood structure. Finally, we combine these network features with the claim-specific features and build a supervised model with fraud in motor insurance as the target variable. Although we build a model for only motor insurance, the network includes claims from all available lines of business. Our results show that models with features derived from the network perform well when detecting fraud and even outperform the models using only the classical claim-specific features. Combining network and claim-specific features further improves the performance of supervised learning models to detect fraud. The resulting model flags highly suspicions claims that need to be further investigated. Our approach provides a guided and intelligent selection of claims and contributes to a more effective fraud investigation process.

BiRank, Bipartite networks, fraud detection, insurance, social networks, supervised learning
0272-4332
Óskarsdóttir, María
1622b6dd-5d25-4228-9418-a1729e9577e0
Ahmed, Waqas
0203f651-62ed-4579-ab8e-d175799ca62c
Antonio, Katrien
21b868fb-debc-495c-87bb-f31f9ae2e79a
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Dendievel, Rémi
def6d19e-22d7-4e2d-a399-19dd9e10658d
Donas, Tom
52ca19b9-4f06-430a-93d3-c39abf836a29
Reynkens, Tom
8c060525-4169-4b00-a7d2-18b891d68abb
Óskarsdóttir, María
1622b6dd-5d25-4228-9418-a1729e9577e0
Ahmed, Waqas
0203f651-62ed-4579-ab8e-d175799ca62c
Antonio, Katrien
21b868fb-debc-495c-87bb-f31f9ae2e79a
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Dendievel, Rémi
def6d19e-22d7-4e2d-a399-19dd9e10658d
Donas, Tom
52ca19b9-4f06-430a-93d3-c39abf836a29
Reynkens, Tom
8c060525-4169-4b00-a7d2-18b891d68abb

Óskarsdóttir, María, Ahmed, Waqas, Antonio, Katrien, Baesens, Bart, Dendievel, Rémi, Donas, Tom and Reynkens, Tom (2021) Social network analytics for supervised fraud detection in insurance. Risk Analysis. (doi:10.1111/risa.13693).

Record type: Article

Abstract

Insurance fraud occurs when policyholders file claims that are exaggerated or based on intentional damages. This contribution develops a fraud detection strategy by extracting insightful information from the social network of a claim. First, we construct a network by linking claims with all their involved parties, including the policyholders, brokers, experts, and garages. Next, we establish fraud as a social phenomenon in the network and use the BiRank algorithm with a fraud-specific query vector to compute a fraud score for each claim. From the network, we extract features related to the fraud scores as well as the claims' neighborhood structure. Finally, we combine these network features with the claim-specific features and build a supervised model with fraud in motor insurance as the target variable. Although we build a model for only motor insurance, the network includes claims from all available lines of business. Our results show that models with features derived from the network perform well when detecting fraud and even outperform the models using only the classical claim-specific features. Combining network and claim-specific features further improves the performance of supervised learning models to detect fraud. The resulting model flags highly suspicions claims that need to be further investigated. Our approach provides a guided and intelligent selection of claims and contributes to a more effective fraud investigation process.

Text
SNAfraud - Accepted Manuscript
Restricted to Repository staff only until 6 February 2023.
Request a copy

More information

Accepted/In Press date: 6 February 2021
e-pub ahead of print date: 6 February 2021
Additional Information: Funding Information: This work was supported by the Ageas Research chair at KU Leuven and KU Leuven's research council (Project COMPACT C24/15/001). This support is gratefully acknowledged. This research has been financed in part by the NeEDS research project, an EC H2020 MSCA RISE project with Grant Agreement Number 822214. Publisher Copyright: © 2021 Society for Risk Analysis Copyright: Copyright 2021 Elsevier B.V., All rights reserved.
Keywords: BiRank, Bipartite networks, fraud detection, insurance, social networks, supervised learning

Identifiers

Local EPrints ID: 448443
URI: http://eprints.soton.ac.uk/id/eprint/448443
ISSN: 0272-4332
PURE UUID: 701b7958-7b70-4dbd-ac00-0eb82db23420
ORCID for Bart Baesens: ORCID iD orcid.org/0000-0002-5831-5668

Catalogue record

Date deposited: 22 Apr 2021 16:45
Last modified: 28 Apr 2022 01:53

Export record

Altmetrics

Contributors

Author: María Óskarsdóttir
Author: Waqas Ahmed
Author: Katrien Antonio
Author: Bart Baesens ORCID iD
Author: Rémi Dendievel
Author: Tom Donas
Author: Tom Reynkens

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×