Abstract

Every online transaction comes with a risk and it is the merchant’s liability to detect and stop fraudulent transactions. Merchants utilize various mechanisms to prevent and manage fraud such as automated fraud detection systems and manual transaction reviews by expert fraud analysts. Many proposed solutions mostly focus on fraud detection accuracy and ignore financial considerations. Also, highly effective manual review process is overlooked. We propose Profit Optimizing Neural Risk Manager (PONRM), a decision maker that (a) constitutes optimal collaboration between machine learning models and human expertise under industrial constraints, (b) is cost and profit sensitive. We suggest directions on how to characterize fraudulent behavior and assess the risk of a transaction. We show that our framework outperforms cost-sensitive and cost-insensitive baselines on three real-world merchant datasets.

Original languageEnglish (US)
Title of host publicationArtificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings
PublisherSpringer New York LLC
Pages323-336
Number of pages14
ISBN (Print)9783319920061
DOIs
StatePublished - Jan 1 2018
Event14th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2018 - Rhodes, Greece
Duration: May 25 2018May 27 2018

Publication series

NameIFIP Advances in Information and Communication Technology
Volume519
ISSN (Print)1868-4238

Other

Other14th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2018
CountryGreece
CityRhodes
Period5/25/185/27/18

Fingerprint

Decision making
Profitability
Costs
Learning systems
Managers
Fraud
Merchants
Fraud detection
Profit

Keywords

  • Cost-sensitive learning
  • E-commerce
  • Fraud detection
  • Risk management

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications
  • Information Systems and Management

Cite this

Yildirim, M. Y., Ozer, M., & Davulcu, H. (2018). Cost-sensitive decision making for online fraud management. In Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings (pp. 323-336). (IFIP Advances in Information and Communication Technology; Vol. 519). Springer New York LLC. https://doi.org/10.1007/978-3-319-92007-8_28

Cost-sensitive decision making for online fraud management. / Yildirim, Mehmet Yigit; Ozer, Mert; Davulcu, Hasan.

Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings. Springer New York LLC, 2018. p. 323-336 (IFIP Advances in Information and Communication Technology; Vol. 519).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yildirim, MY, Ozer, M & Davulcu, H 2018, Cost-sensitive decision making for online fraud management. in Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings. IFIP Advances in Information and Communication Technology, vol. 519, Springer New York LLC, pp. 323-336, 14th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2018, Rhodes, Greece, 5/25/18. https://doi.org/10.1007/978-3-319-92007-8_28
Yildirim MY, Ozer M, Davulcu H. Cost-sensitive decision making for online fraud management. In Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings. Springer New York LLC. 2018. p. 323-336. (IFIP Advances in Information and Communication Technology). https://doi.org/10.1007/978-3-319-92007-8_28
Yildirim, Mehmet Yigit ; Ozer, Mert ; Davulcu, Hasan. / Cost-sensitive decision making for online fraud management. Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings. Springer New York LLC, 2018. pp. 323-336 (IFIP Advances in Information and Communication Technology).
@inproceedings{29e2e2015b1047f7807b5a53c402ed46,
title = "Cost-sensitive decision making for online fraud management",
abstract = "Every online transaction comes with a risk and it is the merchant’s liability to detect and stop fraudulent transactions. Merchants utilize various mechanisms to prevent and manage fraud such as automated fraud detection systems and manual transaction reviews by expert fraud analysts. Many proposed solutions mostly focus on fraud detection accuracy and ignore financial considerations. Also, highly effective manual review process is overlooked. We propose Profit Optimizing Neural Risk Manager (PONRM), a decision maker that (a) constitutes optimal collaboration between machine learning models and human expertise under industrial constraints, (b) is cost and profit sensitive. We suggest directions on how to characterize fraudulent behavior and assess the risk of a transaction. We show that our framework outperforms cost-sensitive and cost-insensitive baselines on three real-world merchant datasets.",
keywords = "Cost-sensitive learning, E-commerce, Fraud detection, Risk management",
author = "Yildirim, {Mehmet Yigit} and Mert Ozer and Hasan Davulcu",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-92007-8_28",
language = "English (US)",
isbn = "9783319920061",
series = "IFIP Advances in Information and Communication Technology",
publisher = "Springer New York LLC",
pages = "323--336",
booktitle = "Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings",

}

TY - GEN

T1 - Cost-sensitive decision making for online fraud management

AU - Yildirim, Mehmet Yigit

AU - Ozer, Mert

AU - Davulcu, Hasan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Every online transaction comes with a risk and it is the merchant’s liability to detect and stop fraudulent transactions. Merchants utilize various mechanisms to prevent and manage fraud such as automated fraud detection systems and manual transaction reviews by expert fraud analysts. Many proposed solutions mostly focus on fraud detection accuracy and ignore financial considerations. Also, highly effective manual review process is overlooked. We propose Profit Optimizing Neural Risk Manager (PONRM), a decision maker that (a) constitutes optimal collaboration between machine learning models and human expertise under industrial constraints, (b) is cost and profit sensitive. We suggest directions on how to characterize fraudulent behavior and assess the risk of a transaction. We show that our framework outperforms cost-sensitive and cost-insensitive baselines on three real-world merchant datasets.

AB - Every online transaction comes with a risk and it is the merchant’s liability to detect and stop fraudulent transactions. Merchants utilize various mechanisms to prevent and manage fraud such as automated fraud detection systems and manual transaction reviews by expert fraud analysts. Many proposed solutions mostly focus on fraud detection accuracy and ignore financial considerations. Also, highly effective manual review process is overlooked. We propose Profit Optimizing Neural Risk Manager (PONRM), a decision maker that (a) constitutes optimal collaboration between machine learning models and human expertise under industrial constraints, (b) is cost and profit sensitive. We suggest directions on how to characterize fraudulent behavior and assess the risk of a transaction. We show that our framework outperforms cost-sensitive and cost-insensitive baselines on three real-world merchant datasets.

KW - Cost-sensitive learning

KW - E-commerce

KW - Fraud detection

KW - Risk management

UR - http://www.scopus.com/inward/record.url?scp=85049595509&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049595509&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-92007-8_28

DO - 10.1007/978-3-319-92007-8_28

M3 - Conference contribution

AN - SCOPUS:85049595509

SN - 9783319920061

T3 - IFIP Advances in Information and Communication Technology

SP - 323

EP - 336

BT - Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings

PB - Springer New York LLC

ER -