Comparing the performance of some neural fraud detectors in telecommunications

Fraud detection in telecommunications is an area where pattern recognition and so called “intelligent” techniques have found widespread use. Due to fraud, companies suffer not only direct economic losses but also the risk of bad publicity. In this paper real cases of fraud are being treated in order to develop a detection system with low number of false alarms and good sensitivity. Call data records provide a number of measures that can be used to discriminate fraudulent activities from correct ones. Three neural networks schemes have been applied to such data comparing latter their results with new cases.