Combining Discriminant Analysis and Neural Networks for Fraud Detection on the Base of Complex Event Processing

A new approach to detect suspicious, unknown event patterns in the field of fraud detection by using a combination of discriminant analysis and neural network techniques is presented. The approach is embedded in a Complex Event Processing (CEP) engine. CEP is an emerging technology for detecting known patterns of events and aggregating them as complex events at a higher level of analysis in real-time. Detection systems can be differentiated in rule based systems and those based on statistical methods. In order to reach the goal of finding unknown fraud patterns, several statistical methods are discussed. On this background, first experimental results of our approach as a combination of CEP, discriminant analysis and neural networks are presented.