The advent of electronic commerce (e-commerce) has marked a significant change in the way business now approach the implementation of their sales and marketing strategies. Electronic commerce growth has been accompanied by an increase in fraudulent practices. Researchers have proposed rules-based auditing systems for electronic commerce transactions, but they highly depend on the auditor’s knowledge of ecommerce fraud (Wong et al., 2000). While fraud patterns may occur, the management, control, and application of these patterns is difficult due to the increasing number of online transactions currently handled by e-commerce systems. In this paper, we present research in progress of the prototype of an extension to e-commerce auditing systems that use data mining techniques to generate rules from fraud patterns. Subsequently, the system applies these rules to e-commerce databases with the aim of isolating those transactions that have a high chance of being fraudulent.
[1]
Arno Siebes,et al.
Data Mining: the search for knowledge in databases.
,
1994
.
[2]
C. Richard Baker,et al.
An analysis of fraud on the Internet
,
1999,
Internet Res..
[3]
Ravinder Nath,et al.
Electronic Commerce and the Internet: Issues, Problems, and Perspectives
,
1998
.
[4]
Robert Groth,et al.
Data Mining: Building Competitive Advantage
,
1999
.
[5]
Sebastian Thrun,et al.
The MONK''s Problems-A Performance Comparison of Different Learning Algorithms, CMU-CS-91-197, Sch
,
1991
.
[6]
Teresa F. Lunt,et al.
A survey of intrusion detection techniques
,
1993,
Comput. Secur..