CATCHM: A novel network-based credit card fraud detection method using node representation learning
CATCHM: A novel network-based credit card fraud detection method using node representation learning
Advanced fraud detection systems leverage the digital traces from (credit-card) transactions to detect fraudulent activity in future transactions. Recent research in fraud detection has focused primarily on data analytics combined with manual feature engineering, which is tedious, expensive and requires considerable domain expertise. Furthermore, transactions are often examined in isolation, disregarding the interconnection that exists between them. In this paper, we propose CATCHM, a novel network-based credit card fraud detection method based on representation learning (RL). Through innovative network design, an efficient inductive pooling operator, and careful downstream classifier configuration, we show how network RL can benefit fraud detection by avoiding manual feature engineering and explicitly considering the relational structure of transactions. Extensive empirical evaluation on a real-life credit card dataset shows that CATCHM outperforms state-of-the-art methods, thereby illustrating the practical relevance of this approach for industry.
Credit card fraud, DeepWalk, Fraud detection, Network representation learning
Van Belle, Rafaël
bf6561d9-80da-43d7-a9bd-d33a4f3ba91a
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
De Weerdt, Jochen
1eaa177f-03d0-47e5-b8b6-4fb419d49e47
January 2023
Van Belle, Rafaël
bf6561d9-80da-43d7-a9bd-d33a4f3ba91a
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
De Weerdt, Jochen
1eaa177f-03d0-47e5-b8b6-4fb419d49e47
Van Belle, Rafaël, Baesens, Bart and De Weerdt, Jochen
(2023)
CATCHM: A novel network-based credit card fraud detection method using node representation learning.
Decision Support Systems, 164, [113866].
(doi:10.1016/j.dss.2022.113866).
Abstract
Advanced fraud detection systems leverage the digital traces from (credit-card) transactions to detect fraudulent activity in future transactions. Recent research in fraud detection has focused primarily on data analytics combined with manual feature engineering, which is tedious, expensive and requires considerable domain expertise. Furthermore, transactions are often examined in isolation, disregarding the interconnection that exists between them. In this paper, we propose CATCHM, a novel network-based credit card fraud detection method based on representation learning (RL). Through innovative network design, an efficient inductive pooling operator, and careful downstream classifier configuration, we show how network RL can benefit fraud detection by avoiding manual feature engineering and explicitly considering the relational structure of transactions. Extensive empirical evaluation on a real-life credit card dataset shows that CATCHM outperforms state-of-the-art methods, thereby illustrating the practical relevance of this approach for industry.
Text
DSS
- Accepted Manuscript
Text
DSS
- Accepted Manuscript
Text
1-s2.0-S0167923622001373-main
- Proof
Restricted to Repository staff only
Request a copy
More information
Accepted/In Press date: 29 August 2022
e-pub ahead of print date: 2 September 2022
Published date: January 2023
Additional Information:
Funding Information:
This research was supported by the Research Foundation Flanders [Grant number 180319 ] and was financed in part by the EC H2020 MSCA RISE NeEDS Project [Grant agreement ID: 822214 ].
Funding Information:
This research was supported by Research Foundation Flanders [Grant number 180319 ] and was financed in part by the EC H2020 MSCA RISE NeEDS Project [Grant agreement ID: 822214 ].
Publisher Copyright:
© 2022 Elsevier B.V.
Keywords:
Credit card fraud, DeepWalk, Fraud detection, Network representation learning
Identifiers
Local EPrints ID: 471242
URI: http://eprints.soton.ac.uk/id/eprint/471242
ISSN: 0167-9236
PURE UUID: ce1ed7f9-345e-47fb-b506-2b1eeea67c75
Catalogue record
Date deposited: 01 Nov 2022 17:40
Last modified: 17 Mar 2024 07:32
Export record
Altmetrics
Contributors
Author:
Rafaël Van Belle
Author:
Jochen De Weerdt
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
