转发
上传时间: 2015-03-13 浏览次数:751次
Mobileum Announces Anti-Fraud Analytics that Discovers Telecom Frauds Before They Occur
Fri, Mar 13, 2015
BARCELONA, Spain -- Mobileum, the leader in analytics solutions for telecom business transformation, today announced Mobileum Anti-Fraud Analytics, a predictive, machine learning-based fraud prevention solution that helps telecom operators to arrest revenue leakage with real-time fraud detection.
Telecom fraud continues to be a serious menace for the Telecom Operators eroding their profits and impacting their brand image. With over $46 billion in lost revenue, telecom is second only to banks in revenue leakage from fraud. For some operators, losses from fraud are growing faster year-over-year than the service revenue. Conventional Fraud Management Systems understand known frauds and have rules built to detect known ways of committing fraud, but such systems are unable to keep pace with the fraudsters who are constantly innovating and evolving.
"When it comes to telecom fraud there are 'known unknowns' and 'unknown unknowns', which the rule-based fraud management systems cannot detect. And even if these conventional systems belatedly detect new types of fraud, the latency in detection renders it useless because by that time the fraudsters have changed the rules of the game. This year's fraud techniques will not be the same as last year's," said Sudhir Kadam, SVP and Analytics Business Line Head at Mobileum. "Our advanced analytics solution takes mobile operators from an increasingly inefficient, rule-based solutions era to the world of predictive machine learning, without the need to understand complex algorithms to fight fraud and arrest revenue leakage."
Mobileum Anti-Fraud Analytics runs on its patent-pending Big Data and Analytics platform called Wisdom, which can mine through billions of unsuspected usage transactions in real-time to discover anomalous patterns of emerging fraudulent behaviors. This helps widen the net to trap the deviations in known types of frauds, and identify unknown frauds, across Voice, Data and SMS, as well as international and roaming fraud scenarios.
Mobileum mentioned that a Tier-1 US mobile operator signed up as the first customer for Anti-Fraud Analytics in Dec 2014.
Telecom fraud continues to be a serious menace for the Telecom Operators eroding their profits and impacting their brand image. With over $46 billion in lost revenue, telecom is second only to banks in revenue leakage from fraud. For some operators, losses from fraud are growing faster year-over-year than the service revenue. Conventional Fraud Management Systems understand known frauds and have rules built to detect known ways of committing fraud, but such systems are unable to keep pace with the fraudsters who are constantly innovating and evolving.
"When it comes to telecom fraud there are 'known unknowns' and 'unknown unknowns', which the rule-based fraud management systems cannot detect. And even if these conventional systems belatedly detect new types of fraud, the latency in detection renders it useless because by that time the fraudsters have changed the rules of the game. This year's fraud techniques will not be the same as last year's," said Sudhir Kadam, SVP and Analytics Business Line Head at Mobileum. "Our advanced analytics solution takes mobile operators from an increasingly inefficient, rule-based solutions era to the world of predictive machine learning, without the need to understand complex algorithms to fight fraud and arrest revenue leakage."
Mobileum Anti-Fraud Analytics runs on its patent-pending Big Data and Analytics platform called Wisdom, which can mine through billions of unsuspected usage transactions in real-time to discover anomalous patterns of emerging fraudulent behaviors. This helps widen the net to trap the deviations in known types of frauds, and identify unknown frauds, across Voice, Data and SMS, as well as international and roaming fraud scenarios.
Mobileum mentioned that a Tier-1 US mobile operator signed up as the first customer for Anti-Fraud Analytics in Dec 2014.