Real-time Anomaly Detection in Streaming Cellular Network Data
Argyle Data and Carnegie Mellon University Silicon Valley have collaborated to create a new research paper, Real-time Anomaly Detection in Streaming Cellular Network Data, that validates an adaptive approach for the identification of anomalous activity in telecommunications networks using supervised and unsupervised machine learning.
Approaches currently used to detect fraud in communications networks typically rely on static rules with pre-set thresholds. In this work, Senior Author Dr. Mengshoel and First Author David Staub propose and validate a machine learning-based approach that automatically learns the difference between normal and anomalous call patterns based on historical usage data.
The complete paper has been submitted for presentation at academic conferences during early 2017. To download the executive preview of the paper, please register below.