SAN MATEO, CA--(Marketwired - January 04, 2017) - In 2017, machine learning 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, Vice President 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. 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 (e.g. 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."
Based on customer feedback, Argyle Data says the following rank among the top communications service provider (CSP) concerns for 2017:
- Subscription fraud and dealer fraud: these are currently the most prominent fraud issues plaguing mobile operators, the complexity of the fraud, the volume of data and the need to need to react in real time all require machine learning to stop the revenue bleed.
- Fraud using mobile data services and IP applications will absorb greater amounts of CSP focus.
- Call bypass: the growing popularity of voice and video calling from applications such as WhatsApp, WeChat and Viber will have an increasingly significant impact on carriers' revenues.
- Mobile voice is going the way of the dodo. Most smartphone conversations today take place over IP; data-only phones and plans are becoming more mainstream worldwide.
- Identifying, analyzing and monetizing IP-based traffic to stem the decline in call termination revenues will be a key focus area for 2017.
- The explosion of IoT devices across communications networks means CSPs have to look at all IP packets as they come back into the network to make sure they haven't been compromised.
"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."
Approaches currently used by mobile communications providers to detect fraud typically rely on static rules with pre-set thresholds. Moreover, such solutions cannot address issues on the data plane. Argyle Data's machine learning algorithms allow analysis of traffic across the voice and data planes. Since more and more fraud will occur on the data network in future, gaining visibility into the characteristics of data usage will be paramount. In particular, this is increasingly important for control and management of Over-the-Top (OTT) applications and IoT devices, and will enable operators to rapidly shut down attacks such as DDoS attacks leveraging cheap connected cameras in October 2016.
"Very few analytics applications currently provide the insight and understanding of applications and volumes of data being consumed by mobile subscribers. This knowledge will be crucial to mobile carriers' operations in 2017, which Argyle Data sees as a big differentiator and opportunity in 2017," said Stapleton.
About Argyle Data
Argyle Data is used by the world's leading mobile operators to detect mobile fraud and OTT threats that cost the industry $38 billion per year. Argyle Data's industry-leading native Hadoop application suite uses the latest machine learning technologies against a unique, comprehensive data lake to give communications service providers a 360-degree view of user activities, allowing them to detect in real time the previously undiscoverable revenue threats and attack patterns being waged against their networks. To learn more please visit: