AAAI-97 Workshop
AI Approaches to Fraud Detection and Risk Management

This workshop was held on Sunday, July 27 in conjunction with the AAAI-97 conference in Providence, Rhode Island.

Description

Fraud detection and risk management involve monitoring the behavior of populations of users in order to estimate, detect or avoid undesirable behavior. Undesirable behavior is a broad term including delinquency, fraud, intrusion and account defaulting. This workshop brought together researchers in these areas to discuss approaches and experiences in dealing with the critical issues:

large volumes of data
highly skewed distributions
changing distributions
widely varying error costs, and costs changing over time
adaptation of undesirable behavior to detection techniques
changing patterns of legitimate behavior
trading accuracy for timely decisions
social issues (privacy, discrimination, "redlining")

Topics

Papers on the following areas were invited:

Credit/calling card fraud Computer/network intrusion

Internet transaction fraud Insurance fraud

Cellular fraud Insider trading

Credit rating/approval Prediction of delinquency/bad debt

Machine learning Neural networks

Probabilistic modeling Decision Theory

Genetic algorithms Knowledge discovery and data mining

Knowledge-based systems Statistical approaches

Accepted papers

Schedule

Working Notes

The working notes are available as a technical report from AAAI. Ordering information is here.

Organizing Committee

Tom Fawcett

NYNEX Science and Technology

(Now at HP Labs)

tom_fawcett@hp.com

Ira Haimowitz

GE Corporate Research and Development

haimowitz@crd.ge.com

Foster Provost

NYNEX Science and Technology

foster@nynexst.com

Sal Stolfo

Columbia University

stolfo@cs.columbia.edu

Other Sources of Information

Journal article, ``Adaptive Fraud Detection``, by Fawcett and Provost.
General information about the AAAI-97 conference
Information about the workshops at AAAI-97

Tom Fawcett / tom_fawcett@hp.com

Modified: 26-Jun-2001

Credit/calling card fraud	Computer/network intrusion
Internet transaction fraud	Insurance fraud
Cellular fraud	Insider trading
Credit rating/approval	Prediction of delinquency/bad debt
Machine learning	Neural networks
Probabilistic modeling	Decision Theory
Genetic algorithms	Knowledge discovery and data mining
Knowledge-based systems	Statistical approaches

AAAI-97 Workshop AI Approaches to Fraud Detection and Risk Management