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 language | English (US) |
|---|---|
| Title of host publication | Artificial Intelligence Applications and Innovations - 14th IFIP WG 12.5 International Conference, AIAI 2018, Proceedings |
| Publisher | Springer New York LLC |
| Pages | 323-336 |
| Number of pages | 14 |
| ISBN (Print) | 9783319920061 |
| DOIs | |
| State | Published - Jan 1 2018 |
| Event | 14th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2018 - Rhodes, Greece Duration: May 25 2018 → May 27 2018 |
Publication series
| Name | IFIP Advances in Information and Communication Technology |
|---|---|
| Volume | 519 |
| ISSN (Print) | 1868-4238 |
Other
| Other | 14th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2018 |
|---|---|
| Country | Greece |
| City | Rhodes |
| Period | 5/25/18 → 5/27/18 |
Fingerprint
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
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 proceeding › Conference contribution
}
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 -