Rudolf: Interactive Rule Refinement System for Fraud Detection. Milo, T., Novgorodov, S., & Tan, W. Proceedings of the Vldb Endowment, 9(13):1465-1468, 2016.
Paper abstract bibtex Credit card frauds are unauthorized transactions that are made or
attempted by a person or an organization that is not authorized by the
card holders. In addition to machine learning-based techniques, credit
card companies often employ domain experts to manually specify rules
that exploit domain knowledge for improving the detection process. Over
time, however, as new (fraudulent and legitimate) transaction arrive,
these rules need to be updated and refined to capture the evolving
(fraud and legitimate) activity patterns. The goal of the RUDOLF system
that is demonstrated here is to guide and assist domain experts in this
challenging task.
RUDOLF automatically determines a best set of candidate adaptations to
existing rules to capture all fraudulent transactions and, respectively,
omit all legitimate transactions. The proposed modifications can then be
further refined by domain experts based on their domain knowledge, and
the process can be repeated until the experts are satisfied with the
resulting rules. Our experimental results on real-life datasets
demonstrate the effectiveness and efficiency of our approach. We
showcase RUDOLF with two demonstration scenarios: detecting credit card
frauds and network attacks. Our demonstration will engage the VLDB
audience by allowing them to play the role of a security expert, a
credit card fraudster, or a network attacker.
@article{
title = {Rudolf: Interactive Rule Refinement System for Fraud Detection},
type = {article},
year = {2016},
identifiers = {[object Object]},
pages = {1465-1468},
volume = {9},
id = {cbb76e09-2e62-3206-a3ad-7e69612dcd2a},
created = {2018-01-04T18:35:21.675Z},
file_attached = {true},
profile_id = {0ecaa748-3fac-3117-bdf6-9c4c3c7996d4},
group_id = {d5687afc-7996-37cd-8cc9-b955ea15e0aa},
last_modified = {2018-01-10T17:12:33.401Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Milo2016a},
private_publication = {false},
abstract = {Credit card frauds are unauthorized transactions that are made or
attempted by a person or an organization that is not authorized by the
card holders. In addition to machine learning-based techniques, credit
card companies often employ domain experts to manually specify rules
that exploit domain knowledge for improving the detection process. Over
time, however, as new (fraudulent and legitimate) transaction arrive,
these rules need to be updated and refined to capture the evolving
(fraud and legitimate) activity patterns. The goal of the RUDOLF system
that is demonstrated here is to guide and assist domain experts in this
challenging task.
RUDOLF automatically determines a best set of candidate adaptations to
existing rules to capture all fraudulent transactions and, respectively,
omit all legitimate transactions. The proposed modifications can then be
further refined by domain experts based on their domain knowledge, and
the process can be repeated until the experts are satisfied with the
resulting rules. Our experimental results on real-life datasets
demonstrate the effectiveness and efficiency of our approach. We
showcase RUDOLF with two demonstration scenarios: detecting credit card
frauds and network attacks. Our demonstration will engage the VLDB
audience by allowing them to play the role of a security expert, a
credit card fraudster, or a network attacker.},
bibtype = {article},
author = {Milo, Tova and Novgorodov, Slava and Tan, Wang-Chiew},
journal = {Proceedings of the Vldb Endowment},
number = {13}
}
Downloads: 0
{"_id":"Bbzd9hy82BqGturej","bibbaseid":"milo-novgorodov-tan-rudolfinteractiverulerefinementsystemforfrauddetection-2016","authorIDs":[],"author_short":["Milo, T.","Novgorodov, S.","Tan, W."],"bibdata":{"title":"Rudolf: Interactive Rule Refinement System for Fraud Detection","type":"article","year":"2016","identifiers":"[object Object]","pages":"1465-1468","volume":"9","id":"cbb76e09-2e62-3206-a3ad-7e69612dcd2a","created":"2018-01-04T18:35:21.675Z","file_attached":"true","profile_id":"0ecaa748-3fac-3117-bdf6-9c4c3c7996d4","group_id":"d5687afc-7996-37cd-8cc9-b955ea15e0aa","last_modified":"2018-01-10T17:12:33.401Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Milo2016a","private_publication":false,"abstract":"Credit card frauds are unauthorized transactions that are made or\nattempted by a person or an organization that is not authorized by the\ncard holders. In addition to machine learning-based techniques, credit\ncard companies often employ domain experts to manually specify rules\nthat exploit domain knowledge for improving the detection process. Over\ntime, however, as new (fraudulent and legitimate) transaction arrive,\nthese rules need to be updated and refined to capture the evolving\n(fraud and legitimate) activity patterns. The goal of the RUDOLF system\nthat is demonstrated here is to guide and assist domain experts in this\nchallenging task.\nRUDOLF automatically determines a best set of candidate adaptations to\nexisting rules to capture all fraudulent transactions and, respectively,\nomit all legitimate transactions. The proposed modifications can then be\nfurther refined by domain experts based on their domain knowledge, and\nthe process can be repeated until the experts are satisfied with the\nresulting rules. Our experimental results on real-life datasets\ndemonstrate the effectiveness and efficiency of our approach. We\nshowcase RUDOLF with two demonstration scenarios: detecting credit card\nfrauds and network attacks. Our demonstration will engage the VLDB\naudience by allowing them to play the role of a security expert, a\ncredit card fraudster, or a network attacker.","bibtype":"article","author":"Milo, Tova and Novgorodov, Slava and Tan, Wang-Chiew","journal":"Proceedings of the Vldb Endowment","number":"13","bibtex":"@article{\n title = {Rudolf: Interactive Rule Refinement System for Fraud Detection},\n type = {article},\n year = {2016},\n identifiers = {[object Object]},\n pages = {1465-1468},\n volume = {9},\n id = {cbb76e09-2e62-3206-a3ad-7e69612dcd2a},\n created = {2018-01-04T18:35:21.675Z},\n file_attached = {true},\n profile_id = {0ecaa748-3fac-3117-bdf6-9c4c3c7996d4},\n group_id = {d5687afc-7996-37cd-8cc9-b955ea15e0aa},\n last_modified = {2018-01-10T17:12:33.401Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Milo2016a},\n private_publication = {false},\n abstract = {Credit card frauds are unauthorized transactions that are made or\nattempted by a person or an organization that is not authorized by the\ncard holders. In addition to machine learning-based techniques, credit\ncard companies often employ domain experts to manually specify rules\nthat exploit domain knowledge for improving the detection process. Over\ntime, however, as new (fraudulent and legitimate) transaction arrive,\nthese rules need to be updated and refined to capture the evolving\n(fraud and legitimate) activity patterns. The goal of the RUDOLF system\nthat is demonstrated here is to guide and assist domain experts in this\nchallenging task.\nRUDOLF automatically determines a best set of candidate adaptations to\nexisting rules to capture all fraudulent transactions and, respectively,\nomit all legitimate transactions. The proposed modifications can then be\nfurther refined by domain experts based on their domain knowledge, and\nthe process can be repeated until the experts are satisfied with the\nresulting rules. Our experimental results on real-life datasets\ndemonstrate the effectiveness and efficiency of our approach. We\nshowcase RUDOLF with two demonstration scenarios: detecting credit card\nfrauds and network attacks. Our demonstration will engage the VLDB\naudience by allowing them to play the role of a security expert, a\ncredit card fraudster, or a network attacker.},\n bibtype = {article},\n author = {Milo, Tova and Novgorodov, Slava and Tan, Wang-Chiew},\n journal = {Proceedings of the Vldb Endowment},\n number = {13}\n}","author_short":["Milo, T.","Novgorodov, S.","Tan, W."],"urls":{"Paper":"https://bibbase.org/service/mendeley/7127e9bf-bb7e-31a5-a06e-59fccf53ff81/file/264749b4-30a4-3b1f-2579-2511f262e84e/p1465_milo.pdf.pdf"},"bibbaseid":"milo-novgorodov-tan-rudolfinteractiverulerefinementsystemforfrauddetection-2016","role":"author","downloads":0},"bibtype":"article","creationDate":"2020-06-19T09:41:42.211Z","downloads":0,"keywords":[],"search_terms":["rudolf","interactive","rule","refinement","system","fraud","detection","milo","novgorodov","tan"],"title":"Rudolf: Interactive Rule Refinement System for Fraud Detection","year":2016}