eRiskCom: an e-commerce risky community detection platform
Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users obs...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Liu, Fanzhen [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
|---|
| Übergeordnetes Werk: |
Enthalten in: The VLDB journal - Springer Berlin Heidelberg, 1992, 31(2022), 5 vom: 17. Jan., Seite 1085-1101 |
|---|---|
| Übergeordnetes Werk: |
volume:31 ; year:2022 ; number:5 ; day:17 ; month:01 ; pages:1085-1101 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00778-021-00723-z |
|---|
| Katalog-ID: |
OLC2079438166 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2079438166 | ||
| 003 | DE-627 | ||
| 005 | 20230506061456.0 | ||
| 007 | tu | ||
| 008 | 221220s2022 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00778-021-00723-z |2 doi | |
| 035 | |a (DE-627)OLC2079438166 | ||
| 035 | |a (DE-He213)s00778-021-00723-z-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q VZ |
| 100 | 1 | |a Liu, Fanzhen |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a eRiskCom: an e-commerce risky community detection platform |
| 264 | 1 | |c 2022 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 | ||
| 520 | |a Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. | ||
| 650 | 4 | |a Community detection | |
| 650 | 4 | |a E-commerce | |
| 650 | 4 | |a Telecom fraud | |
| 650 | 4 | |a Insurance fraud | |
| 650 | 4 | |a Transaction fraud | |
| 650 | 4 | |a Fraud detection | |
| 650 | 4 | |a Subgraph pattern | |
| 650 | 4 | |a Graph mining | |
| 700 | 1 | |a Li, Zhao |4 aut | |
| 700 | 1 | |a Wang, Baokun |4 aut | |
| 700 | 1 | |a Wu, Jia |4 aut | |
| 700 | 1 | |a Yang, Jian |4 aut | |
| 700 | 1 | |a Huang, Jiaming |4 aut | |
| 700 | 1 | |a Zhang, Yiqing |4 aut | |
| 700 | 1 | |a Wang, Weiqiang |4 aut | |
| 700 | 1 | |a Xue, Shan |4 aut | |
| 700 | 1 | |a Nepal, Surya |4 aut | |
| 700 | 1 | |a Sheng, Quan Z. |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The VLDB journal |d Springer Berlin Heidelberg, 1992 |g 31(2022), 5 vom: 17. Jan., Seite 1085-1101 |w (DE-627)170933059 |w (DE-600)1129061-4 |w (DE-576)032856466 |x 1066-8888 |7 nnns |
| 773 | 1 | 8 | |g volume:31 |g year:2022 |g number:5 |g day:17 |g month:01 |g pages:1085-1101 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00778-021-00723-z |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_30 | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4277 | ||
| 951 | |a AR | ||
| 952 | |d 31 |j 2022 |e 5 |b 17 |c 01 |h 1085-1101 | ||
| author_variant |
f l fl z l zl b w bw j w jw j y jy j h jh y z yz w w ww s x sx s n sn q z s qz qzs |
|---|---|
| matchkey_str |
article:10668888:2022----::rscmncmecrsyomntdt |
| hierarchy_sort_str |
2022 |
| publishDate |
2022 |
| allfields |
10.1007/s00778-021-00723-z doi (DE-627)OLC2079438166 (DE-He213)s00778-021-00723-z-p DE-627 ger DE-627 rakwb eng 004 VZ Liu, Fanzhen verfasserin aut eRiskCom: an e-commerce risky community detection platform 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. Community detection E-commerce Telecom fraud Insurance fraud Transaction fraud Fraud detection Subgraph pattern Graph mining Li, Zhao aut Wang, Baokun aut Wu, Jia aut Yang, Jian aut Huang, Jiaming aut Zhang, Yiqing aut Wang, Weiqiang aut Xue, Shan aut Nepal, Surya aut Sheng, Quan Z. aut Enthalten in The VLDB journal Springer Berlin Heidelberg, 1992 31(2022), 5 vom: 17. Jan., Seite 1085-1101 (DE-627)170933059 (DE-600)1129061-4 (DE-576)032856466 1066-8888 nnns volume:31 year:2022 number:5 day:17 month:01 pages:1085-1101 https://doi.org/10.1007/s00778-021-00723-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_30 GBV_ILN_2018 GBV_ILN_4277 AR 31 2022 5 17 01 1085-1101 |
| spelling |
10.1007/s00778-021-00723-z doi (DE-627)OLC2079438166 (DE-He213)s00778-021-00723-z-p DE-627 ger DE-627 rakwb eng 004 VZ Liu, Fanzhen verfasserin aut eRiskCom: an e-commerce risky community detection platform 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. Community detection E-commerce Telecom fraud Insurance fraud Transaction fraud Fraud detection Subgraph pattern Graph mining Li, Zhao aut Wang, Baokun aut Wu, Jia aut Yang, Jian aut Huang, Jiaming aut Zhang, Yiqing aut Wang, Weiqiang aut Xue, Shan aut Nepal, Surya aut Sheng, Quan Z. aut Enthalten in The VLDB journal Springer Berlin Heidelberg, 1992 31(2022), 5 vom: 17. Jan., Seite 1085-1101 (DE-627)170933059 (DE-600)1129061-4 (DE-576)032856466 1066-8888 nnns volume:31 year:2022 number:5 day:17 month:01 pages:1085-1101 https://doi.org/10.1007/s00778-021-00723-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_30 GBV_ILN_2018 GBV_ILN_4277 AR 31 2022 5 17 01 1085-1101 |
| allfields_unstemmed |
10.1007/s00778-021-00723-z doi (DE-627)OLC2079438166 (DE-He213)s00778-021-00723-z-p DE-627 ger DE-627 rakwb eng 004 VZ Liu, Fanzhen verfasserin aut eRiskCom: an e-commerce risky community detection platform 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. Community detection E-commerce Telecom fraud Insurance fraud Transaction fraud Fraud detection Subgraph pattern Graph mining Li, Zhao aut Wang, Baokun aut Wu, Jia aut Yang, Jian aut Huang, Jiaming aut Zhang, Yiqing aut Wang, Weiqiang aut Xue, Shan aut Nepal, Surya aut Sheng, Quan Z. aut Enthalten in The VLDB journal Springer Berlin Heidelberg, 1992 31(2022), 5 vom: 17. Jan., Seite 1085-1101 (DE-627)170933059 (DE-600)1129061-4 (DE-576)032856466 1066-8888 nnns volume:31 year:2022 number:5 day:17 month:01 pages:1085-1101 https://doi.org/10.1007/s00778-021-00723-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_30 GBV_ILN_2018 GBV_ILN_4277 AR 31 2022 5 17 01 1085-1101 |
| allfieldsGer |
10.1007/s00778-021-00723-z doi (DE-627)OLC2079438166 (DE-He213)s00778-021-00723-z-p DE-627 ger DE-627 rakwb eng 004 VZ Liu, Fanzhen verfasserin aut eRiskCom: an e-commerce risky community detection platform 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. Community detection E-commerce Telecom fraud Insurance fraud Transaction fraud Fraud detection Subgraph pattern Graph mining Li, Zhao aut Wang, Baokun aut Wu, Jia aut Yang, Jian aut Huang, Jiaming aut Zhang, Yiqing aut Wang, Weiqiang aut Xue, Shan aut Nepal, Surya aut Sheng, Quan Z. aut Enthalten in The VLDB journal Springer Berlin Heidelberg, 1992 31(2022), 5 vom: 17. Jan., Seite 1085-1101 (DE-627)170933059 (DE-600)1129061-4 (DE-576)032856466 1066-8888 nnns volume:31 year:2022 number:5 day:17 month:01 pages:1085-1101 https://doi.org/10.1007/s00778-021-00723-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_30 GBV_ILN_2018 GBV_ILN_4277 AR 31 2022 5 17 01 1085-1101 |
| allfieldsSound |
10.1007/s00778-021-00723-z doi (DE-627)OLC2079438166 (DE-He213)s00778-021-00723-z-p DE-627 ger DE-627 rakwb eng 004 VZ Liu, Fanzhen verfasserin aut eRiskCom: an e-commerce risky community detection platform 2022 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. Community detection E-commerce Telecom fraud Insurance fraud Transaction fraud Fraud detection Subgraph pattern Graph mining Li, Zhao aut Wang, Baokun aut Wu, Jia aut Yang, Jian aut Huang, Jiaming aut Zhang, Yiqing aut Wang, Weiqiang aut Xue, Shan aut Nepal, Surya aut Sheng, Quan Z. aut Enthalten in The VLDB journal Springer Berlin Heidelberg, 1992 31(2022), 5 vom: 17. Jan., Seite 1085-1101 (DE-627)170933059 (DE-600)1129061-4 (DE-576)032856466 1066-8888 nnns volume:31 year:2022 number:5 day:17 month:01 pages:1085-1101 https://doi.org/10.1007/s00778-021-00723-z lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_30 GBV_ILN_2018 GBV_ILN_4277 AR 31 2022 5 17 01 1085-1101 |
| language |
English |
| source |
Enthalten in The VLDB journal 31(2022), 5 vom: 17. Jan., Seite 1085-1101 volume:31 year:2022 number:5 day:17 month:01 pages:1085-1101 |
| sourceStr |
Enthalten in The VLDB journal 31(2022), 5 vom: 17. Jan., Seite 1085-1101 volume:31 year:2022 number:5 day:17 month:01 pages:1085-1101 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Community detection E-commerce Telecom fraud Insurance fraud Transaction fraud Fraud detection Subgraph pattern Graph mining |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
The VLDB journal |
| authorswithroles_txt_mv |
Liu, Fanzhen @@aut@@ Li, Zhao @@aut@@ Wang, Baokun @@aut@@ Wu, Jia @@aut@@ Yang, Jian @@aut@@ Huang, Jiaming @@aut@@ Zhang, Yiqing @@aut@@ Wang, Weiqiang @@aut@@ Xue, Shan @@aut@@ Nepal, Surya @@aut@@ Sheng, Quan Z. @@aut@@ |
| publishDateDaySort_date |
2022-01-17T00:00:00Z |
| hierarchy_top_id |
170933059 |
| dewey-sort |
14 |
| id |
OLC2079438166 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2079438166</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506061456.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00778-021-00723-z</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2079438166</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00778-021-00723-z-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Liu, Fanzhen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">eRiskCom: an e-commerce risky community detection platform</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Community detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">E-commerce</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Telecom fraud</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Insurance fraud</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Transaction fraud</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fraud detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Subgraph pattern</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Graph mining</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Zhao</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Baokun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wu, Jia</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yang, Jian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Huang, Jiaming</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yiqing</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Weiqiang</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xue, Shan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Nepal, Surya</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sheng, Quan Z.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">The VLDB journal</subfield><subfield code="d">Springer Berlin Heidelberg, 1992</subfield><subfield code="g">31(2022), 5 vom: 17. Jan., Seite 1085-1101</subfield><subfield code="w">(DE-627)170933059</subfield><subfield code="w">(DE-600)1129061-4</subfield><subfield code="w">(DE-576)032856466</subfield><subfield code="x">1066-8888</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:31</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:5</subfield><subfield code="g">day:17</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:1085-1101</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00778-021-00723-z</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_30</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">31</subfield><subfield code="j">2022</subfield><subfield code="e">5</subfield><subfield code="b">17</subfield><subfield code="c">01</subfield><subfield code="h">1085-1101</subfield></datafield></record></collection>
|
| author |
Liu, Fanzhen |
| spellingShingle |
Liu, Fanzhen ddc 004 misc Community detection misc E-commerce misc Telecom fraud misc Insurance fraud misc Transaction fraud misc Fraud detection misc Subgraph pattern misc Graph mining eRiskCom: an e-commerce risky community detection platform |
| authorStr |
Liu, Fanzhen |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)170933059 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut aut aut aut aut aut aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1066-8888 |
| topic_title |
004 VZ eRiskCom: an e-commerce risky community detection platform Community detection E-commerce Telecom fraud Insurance fraud Transaction fraud Fraud detection Subgraph pattern Graph mining |
| topic |
ddc 004 misc Community detection misc E-commerce misc Telecom fraud misc Insurance fraud misc Transaction fraud misc Fraud detection misc Subgraph pattern misc Graph mining |
| topic_unstemmed |
ddc 004 misc Community detection misc E-commerce misc Telecom fraud misc Insurance fraud misc Transaction fraud misc Fraud detection misc Subgraph pattern misc Graph mining |
| topic_browse |
ddc 004 misc Community detection misc E-commerce misc Telecom fraud misc Insurance fraud misc Transaction fraud misc Fraud detection misc Subgraph pattern misc Graph mining |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
The VLDB journal |
| hierarchy_parent_id |
170933059 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
The VLDB journal |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)170933059 (DE-600)1129061-4 (DE-576)032856466 |
| title |
eRiskCom: an e-commerce risky community detection platform |
| ctrlnum |
(DE-627)OLC2079438166 (DE-He213)s00778-021-00723-z-p |
| title_full |
eRiskCom: an e-commerce risky community detection platform |
| author_sort |
Liu, Fanzhen |
| journal |
The VLDB journal |
| journalStr |
The VLDB journal |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
txt |
| container_start_page |
1085 |
| author_browse |
Liu, Fanzhen Li, Zhao Wang, Baokun Wu, Jia Yang, Jian Huang, Jiaming Zhang, Yiqing Wang, Weiqiang Xue, Shan Nepal, Surya Sheng, Quan Z. |
| container_volume |
31 |
| class |
004 VZ |
| format_se |
Aufsätze |
| author-letter |
Liu, Fanzhen |
| doi_str_mv |
10.1007/s00778-021-00723-z |
| dewey-full |
004 |
| title_sort |
eriskcom: an e-commerce risky community detection platform |
| title_auth |
eRiskCom: an e-commerce risky community detection platform |
| abstract |
Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
| abstractGer |
Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
| abstract_unstemmed |
Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_30 GBV_ILN_2018 GBV_ILN_4277 |
| container_issue |
5 |
| title_short |
eRiskCom: an e-commerce risky community detection platform |
| url |
https://doi.org/10.1007/s00778-021-00723-z |
| remote_bool |
false |
| author2 |
Li, Zhao Wang, Baokun Wu, Jia Yang, Jian Huang, Jiaming Zhang, Yiqing Wang, Weiqiang Xue, Shan Nepal, Surya Sheng, Quan Z. |
| author2Str |
Li, Zhao Wang, Baokun Wu, Jia Yang, Jian Huang, Jiaming Zhang, Yiqing Wang, Weiqiang Xue, Shan Nepal, Surya Sheng, Quan Z. |
| ppnlink |
170933059 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00778-021-00723-z |
| up_date |
2024-07-04T00:56:05.091Z |
| _version_ |
1803607935646957568 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2079438166</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230506061456.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2022 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00778-021-00723-z</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2079438166</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00778-021-00723-z-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Liu, Fanzhen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">eRiskCom: an e-commerce risky community detection platform</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In e-commerce scenarios, frauds events such as telecom fraud, insurance fraud, and fraudulent transactions, bring a huge amount of loss to merchants or users. Identification of fraudsters helps regulators take measures for targeted control. Given a set of fraudsters and suspicious users observed from victims’ reports, how can we effectively distinguish risky users closely related to them from the others for further investigation by human experts? Fraudsters take camouflage actions to hide from being discovered; complex features on users are hard to deal with; patterns of fraudsters are sometimes difficult to explain by human knowledge; and real-world applications involve millions of users. All this makes the question hard to answer. To this end, we design eRiskCom, an e-commerce risky community detection platform to detect risky groups containing identified fraudsters and other closely related users. With the hypothesis that users who interact frequently with fraudsters are more likely to come from the same “risky community,” we construct a connected graph expanded from the identified fraudsters and suspicious users. Next, graph partition is employed to get knowledge of assignment of identified users to potential risky communities, followed by pruning to discover the core members of each community. Finally, top-K users with a high risk score in the neighborhood of core members of each potential community form a final risky community. The extensive experiments are conducted to analyze the effect of our platform components on the alignment with requirements of practical scenarios, and experimental results further demonstrate that eRiskCom is effective and easy to deploy for real-world applications.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Community detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">E-commerce</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Telecom fraud</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Insurance fraud</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Transaction fraud</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fraud detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Subgraph pattern</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Graph mining</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Zhao</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Baokun</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wu, Jia</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yang, Jian</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Huang, Jiaming</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Yiqing</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Weiqiang</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xue, Shan</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Nepal, Surya</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sheng, Quan Z.</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">The VLDB journal</subfield><subfield code="d">Springer Berlin Heidelberg, 1992</subfield><subfield code="g">31(2022), 5 vom: 17. Jan., Seite 1085-1101</subfield><subfield code="w">(DE-627)170933059</subfield><subfield code="w">(DE-600)1129061-4</subfield><subfield code="w">(DE-576)032856466</subfield><subfield code="x">1066-8888</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:31</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:5</subfield><subfield code="g">day:17</subfield><subfield code="g">month:01</subfield><subfield code="g">pages:1085-1101</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00778-021-00723-z</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_30</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">31</subfield><subfield code="j">2022</subfield><subfield code="e">5</subfield><subfield code="b">17</subfield><subfield code="c">01</subfield><subfield code="h">1085-1101</subfield></datafield></record></collection>
|
| score |
7.401372 |