GOTCHA! Network-based fraud detection for security fraud
GOTCHA! Network-based fraud detection for security fraud
We study the impact of network information for social security fraud detection. In a social security system, companies have to pay taxes to the government. This study aims to identify those companies that intentionally go bankrupt to avoid contributing their taxes. We link companies to each other through their shared resources, because some resources are the instigators of fraud. We introduce GOTCHA!, a new approach to define and extract features from a time-weighted network and to exploit and integrate network-based and intrinsic features in fraud detection. The GOTCHA! propagation algorithm diffuses fraud through the network, labeling the unknown and anticipating future fraud while simultaneously decaying the importance of past fraud. We find that domain-driven network variables have a significant impact on detecting past and future frauds and improve the baseline by detecting up to 55% additional fraudsters over time.
3090-3110
Van Vlasselaer, Veronique
80a16e2b-f1d0-4d27-bec5-fe3669d9477c
Eliassi-Rad, Tina
f7b2b811-0cbc-43d6-8005-49570f41018b
Akoglu, Leman
68ea2210-3c84-4bc5-b56d-7b72d46f5029
Snoeck, Monique
9aee96bc-8a57-4c37-bcd7-e83f0b173ee1
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
September 2017
Van Vlasselaer, Veronique
80a16e2b-f1d0-4d27-bec5-fe3669d9477c
Eliassi-Rad, Tina
f7b2b811-0cbc-43d6-8005-49570f41018b
Akoglu, Leman
68ea2210-3c84-4bc5-b56d-7b72d46f5029
Snoeck, Monique
9aee96bc-8a57-4c37-bcd7-e83f0b173ee1
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Van Vlasselaer, Veronique, Eliassi-Rad, Tina, Akoglu, Leman, Snoeck, Monique and Baesens, Bart
(2017)
GOTCHA! Network-based fraud detection for security fraud.
Management Science, 63 (9), .
(doi:10.1287/mnsc.2016.2489).
Abstract
We study the impact of network information for social security fraud detection. In a social security system, companies have to pay taxes to the government. This study aims to identify those companies that intentionally go bankrupt to avoid contributing their taxes. We link companies to each other through their shared resources, because some resources are the instigators of fraud. We introduce GOTCHA!, a new approach to define and extract features from a time-weighted network and to exploit and integrate network-based and intrinsic features in fraud detection. The GOTCHA! propagation algorithm diffuses fraud through the network, labeling the unknown and anticipating future fraud while simultaneously decaying the importance of past fraud. We find that domain-driven network variables have a significant impact on detecting past and future frauds and improve the baseline by detecting up to 55% additional fraudsters over time.
Text
Gotcha (final) MS
- Accepted Manuscript
More information
Accepted/In Press date: 11 February 2016
e-pub ahead of print date: 14 July 2016
Published date: September 2017
Organisations:
Decision Analytics & Risk, Southampton Business School
Identifiers
Local EPrints ID: 411040
URI: http://eprints.soton.ac.uk/id/eprint/411040
ISSN: 0025-1909
PURE UUID: 93c491c9-0e27-414c-8fe1-afe84ba7c381
Catalogue record
Date deposited: 13 Jun 2017 16:32
Last modified: 16 Mar 2024 05:24
Export record
Altmetrics
Contributors
Author:
Veronique Van Vlasselaer
Author:
Tina Eliassi-Rad
Author:
Leman Akoglu
Author:
Monique Snoeck
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
