CSSE Technical Report UWA - CSSE - 2010 - 001 March 2010 Learning Classi er Systems for Fraud Detection
نویسندگان
چکیده
Fraud is a serious problem that costs the worldwide economy trillions of dollars annually. However, fraud detection is di cult as perpetrators actively attempt to masquerade their actions, among typically overwhelming large volumes of, legitimate activity. In this paper, we investigate the fraud detection problem and examine how learning classi er systems can be applied to it. We describe the common properties of fraud, introducing an abstract problem which can be tuned to exhibit those characteristics. We report experiments on this abstract problem with a popular real-time learning classi er system algorithm; results from our experiments demonstrating that this approach can overcome the di culties inherent to the fraud detection problem. Finally we apply the algorithm to a real-world problem (KDD Cup 1999 network intrusion detection) and show that it can achieve very good performance in this domain.
منابع مشابه
CSSE Technical Report UWA-CSSE-09-002 Arbitrary Gaussian Filtering with 25 Additions and 5 Multiplications per Pixel
Summed area tables, also known as integral images, allow image averaging to be performed very efficiently at a small fixed cost per pixel, independent of averaging filter size. Repeated filtering with averaging filters can be used to approximate Gaussian filtering. Thus a good approximation to Gaussian filtering can be achieved at a fixed cost per pixel independent of filter size. This note des...
متن کاملComparative Experiences with Electronic Process Guide Generator Tools
The primary objective of all software engineering courses is to help students learn how to develop successful software systems with good software engineering practices. Various tools and guidelines are used to assist students to gain the knowledge as much as possible. USC’s Center for Systems and Software Engineering (CSSE) has found that the keystone course in learning software engineering is ...
متن کاملInternational Conference on Computer Science and Software Engineering, CSSE 2008, Volume 6: Graphic Communication / Other Applications, December 12-14, 2008, Wuhan, China
متن کامل
Defending Against Injection Attacks Through Context-Sensitive String Evaluation
Injection vulnerabilities pose a major threat to applicationlevel security. Some of the more common types are SQL injection, crosssite scripting and shell injection vulnerabilities. Existing methods for defending against injection attacks, that is, attacks exploiting these vulnerabilities, rely heavily on the application developers and are therefore error-prone. In this paper we introduce CSSE,...
متن کاملService Learning in Software Engineering and Maintenance
We discuss a service-learning program called EPICS (Engineering Projects In Community Service). More specifically, we describe an effort to incorporate EPICS within Computer Science and Software Engineering curricula at Purdue University and Butler University, respectively. EPICS at Purdue University The EPICS (Engineering Projects In Community Service) program was first created at Purdue Unive...
متن کامل