Combining Data Mining and Machine Learning for Effective User Profiling

This paper describes the automatic design of methods for detecting fraudulent behavior. Much of the de&,, ic nrrnm,-,li~h~rl ,,&,a n .am.L~ nf mn.-h;na lm..~:~~ e-. .. ..--..*.*yYYA’“.. UY.“b Y UISLUY “I III-Yllr IxuIY11~ 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 profiling customer behavior. Specifically, we use a rulelearning program to uncover indicators of fraudulent behavior from a large database of cellular calls. These indicators are used to create profilers, which then serve as features to a system that combines evidence from multiple profilers to generate high-confidence alarms. Experiments indicate that this automatic approach performs nearly as well as the best hand-tuned methods for detecting fraud.