The role of supervised and unsupervised machine learning in detecting and preventing anomalous mobile traffic has been highlighted by the Argyle Data which is a leader in big data/machine learning analytics for mobile providers. The research paper on anomaly detection will be presented at the academy conference in early 2017 by Carnegie Mellon University (CMU) Silicon Valley’s Department of Electrical and Computer Engineering and Argyle Data.
Fraud cocktails is an unpredictable mixture of several fraud types is the major attack strategy nowadays which cost the industry $38 billion in 2015. The preset thresholds are used by the operators can only detect known fraud types which make them unable to detect the fraud in a communication network. The new and evolving mutating attacks which happen on a massive scale drains millions of dollars in a jiffy and the analysts take more time than the attack need to evolve.
Mohan Gyani, a member of the Argyle Data Board of Directors and former president and CEO of AT&T Wireless Mobility said machine learning is the key to the growing need of fraud detection solution for the evolving network crimes. The upcoming research with CMU will address the development in this field but the way Argyle Data is applying it supervised and unsupervised machine learning techniques are exceedingly impressive.