Complex: Applying analytics to stop fraud


By Jason Lane-Sellers, offering manager, fraud and security, Mobileum

Part of the problem with modern fraud techniques is that operators can’t keep up. Fraud methods are becoming more sophisticated and complex. Fraudsters know that most solutions are reactive rather than proactive, and are effectively exploiting the time it takes to discover their new schemes.

Too often, a fraud isn’t even discovered until after the carrier service provider’s bottom line has been severely impacted.  Due to the continually evolving, increasingly complex nature of fraud attacks, service providers are under increased pressure to bridge the gap between providing a high level of customer service and preventing fraud.

Trying to keep up

So how can operators keep up? The answer lies in analytics. carrier service providers need a comprehensive multi-protocol solution that is nimble, fast and adds to an operator’s current system capabilities. An effective defence requires a number of key elements: capturing the appropriate data; filtering and blocking abnormal and suspicious traffic or activities; using advanced analytical methods to stop sophisticated fraud.

Analytics is no longer a large dataset to be assessed after the fact. The leaps made in Big Data and analytics in the past few years means real time, advanced methods of pattern identification can be designed and operated by experienced analytics and fraud professionals.

You must start by using defensive analytics to monitor traffic at all interconnecting points – domestic and international – and capturing data for both inbound and outbound roamers using in-signalling nodes.

In addition to constantly analysing traffic from the various relevant locations, an analytics system is required to filter abnormal and suspicious traffic based on pre-configured rules. Using machine learning outlier detection allows the system to go beyond the rule-based systems and catch the fraud threats at an earlier stage.

Accessing the benefits

By using analytics against fraudsters, you will be able to access many benefits, including accurate insights; the best solutions provide a delicate balance of missing few genuine instances of fraud (false negatives), while at the same time not identifying too many false positives.

Also, simple access for delivery of fraud warnings in clear, easy to understand language and processes, data science that provides advanced machine learning capabilities that utilise supervised and unsupervised machine learning techniques to detect various known and unknown fraud scenarios. And also, active testing, for an agent that is completely configurable and can be scheduled to generate test call results.

The telecoms sector is expanding its services around the world with faster connections and more connected devices. New services create not just new revenue opportunities but also associated risks for operators. The challenge is to secure the upside and, at the same time, minimise potential losses incurred via fraudulent activity.

Fraud is increasingly becoming more difficult to detect and prevent because of the high degree of network complexity and ever evolving use of sophisticated techniques. But with these advancements, CSPs must advance their fraud protection tactics. The use of analytics is the best way to fight new fraud in real-time and, ultimately, stop it in its tracks.

Mobileum helps CSPs to grow and protect their revenues, innovate new business models and digitally engage with their customers.


About Author

Comments are closed.