Combining Data Mining and Machine Learning for Eeective User Prooling

This paper describes the automatic design of methods for detecting fraudulent behavior. Much of the design is accomplished using a series of machine learning methods. In particular, we combine data mining and constructive induction with more standard machine learning techniques to design methods for detecting fraudulent usage of cellular telephones based on pro-ling customer behavior. Speciically, we use a rule-learning program to uncover indicators of fraudulent behavior from a large database of cellular calls. These indicators are used to create proolers, which then serve as features to a system that combines evidence from multiple proolers to generate high-conndence alarms. Experiments indicate that this automatic approach performs nearly as well as the best hand-tuned methods for detecting fraud.