Toward scalable learning with non-uniform class and cost distributions: a case study in credit card fraud detection

Very large databases with skewed class distributions and non-uniform cost per error are not uncommon in real-world data mining tasks. We devised a multi-classifier meta-learning approach to address these three issues. Our empirical results from a credit card fraud detection task indicate that the approach can significantly reduce loss due to illegitimate transactions. Introduction Very large databases with skewed class distributions and non-uniform cost per error are not uncommon in real-world data mining tasks. One such task is credit card fraud detection: the number of fraudulent transactions is small compared to legitimate ones, the amount of financial loss for each fraudulent transaction depends on the amount of transaction and other factors, and millions of transactions occur each day. A similar task is cellular phone fraud detection (Fawcett & Provost 1997). Each of these three issues has not been widely studied in the machine learning research community. Fawcett (1996) summariz...