Deakin home > Deakin University Library > Deakin Research Online > Adaptive communal detection in search of adversarial identity crime

Adaptive communal detection in search of adversarial identity crime

Phua, Clifton, Lee, Vincent, Smith-Miles, Kate and Gayler, Ross 2007, Adaptive communal detection in search of adversarial identity crime, in Proceedings of the 2007 International Workshop on Domain Driven Data Mining : August 12, 2007, San Jose, California, ACM, New York, N.Y, pp. 1-10.

Attached Files (Some files may be inaccessible until you login with your Deakin Research Online credentials)
Name Description MIMEType Size Downloads

Title Adaptive communal detection in search of adversarial identity crime
Author(s) Phua, Clifton
Lee, Vincent
Smith-Miles, Kate
Gayler, Ross
Conference name International Workshop on Domain Driven Data Mining (2007 : San Jose, California)
Conference location San Jose, California
Conference dates 12-15 August 2007
Title of proceedings Proceedings of the 2007 International Workshop on Domain Driven Data Mining : August 12, 2007, San Jose, California
Editor(s) Yu, Philips
Publication date 2007
Conference series International Workshop on Domain Driven Data Mining
Start page 1
End page 10
Publisher ACM
Place of publication New York, N.Y
Keyword(s) adaptive fraud/communal detection
adversarial identity crime
automated credit application stream processing system
Summary This paper is on adaptive real-time searching of credit application data streams for identity crime with many search parameters. Specifically, we concentrated on handling our domain-specific adversarial activity problem with the adaptive Communal Analysis Suspicion Scoring (CASS) algorithm. CASS's main novel theoretical contribution is in the formulation of State-of- Alert (SoA) which sets the condition of reduced, same, or heightened watchfulness; and Parameter-of-Change (PoC) which improves detection ability with pre-defined parameter values for each SoA. With pre-configured SoA policy and PoC strategy, CASS determines when, what, and how much to adapt its search parameters to ongoing adversarial activity. The above approach is validated with three sets of experiments, where each experiment is conducted on several million real credit applications and measured with three appropriate performance metrics. Significant improvements are achieved over previous work, with the discovery of some practical insights of adaptivity into our domain.
ISBN 9781595938466
159593846X
Language eng
Field of Research 080499 Data Format not elsewhere classified
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2007 ACM
Persistent URL http://hdl.handle.net/10536/DRO/DU:30008098

Document type: Conference Paper
Collection: School of Engineering and Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in Deakin Research Online is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 539 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Mon, 29 Sep 2008, 09:04:31 EST