An Online Algorithm for Online Fraud Detection: Definition and Testing

Detecting anomalous pattern and data points when collecting information from online mobile devices is as important as doing it fast, reliably, online, and real time for a number of reasons including fraud detection and anomalous software behavior. We present a general-purpose (that is not context specific) strategy and develop an algorithm to address this. It is based on data-mining techniques and in crude essence, it is a statistical classifier for which the characteristics of the clusters need not to be determined stored