Telcos turn to machine learning as they drown in data

Staff writer
Telco Analytics Asia

Machine learning in 2017 will become a mainstream tool for communications providers struggling to transform data overload into actionable analytics, according to Argyle Data.

 “The telecommunications industry is drowning in data,” said Padraig Stapleton, VP of engineering at Argyle Data. “Functions like support, billing, customer care and marketing, throwing off large amounts of data as a by-product of their activities, the exhaust fumes of data.”

Stapleton said fraud and financial analysts alike are overwhelmed by the struggle to control and harness this fire-hose of information into actionable analytics. There is just too much IP traffic going across mobile networks for humans to review, detect and respond to fraud in the traditional ways such as discovering fraud and writing preventative rules.

Machine learning does all the grunt work for analysts, sifting through data in real time and providing output instantly in understandable, accessible formats,” said Stapleton.

Based on customer feedback, Argyle Data said the following rank among the top communications service provider (CSP) concerns for 2017 — subscription fraud and dealer fraud; fraud using mobile data services and IP applications; call bypass; mobile voice is going extinct; identifying, analyzing and monetizing IP-based traffic; and the explosion of IoT devices across communications networks.

“These issues can only be addressed if CSPs have better insight into voice and data traffic passing through their networks,” added Stapleton. “New machine learning algorithms give them the ability to respond rapidly to new trends, anomalies or threats.”

Commentary

Faster speeds don't always equate a better video experience

Kevin Fitchard/OpenSignal

Analysis of video streaming experiences in 14 Asian countries showed a wide disparity in quality

Kevin Fitchard/OpenSignal

Analysis of video streaming experiences in 14 Asian countries showed a wide disparity in quality

Martin Kurth/Gartner

Network slicing requires a dedicated operational infrastructure encompassing an underlying  cross-domain and per-slice tenant management capability