Bell Canada experienced a 150% improvement in the time it takes to detect fraud losses in a significant portion of its fraud and a 200% improvement in the time required to identify new fraud schemes.
Weren't new technologies supposed to create new revenue opportunities, not problems?
The telecommunications industry loses close to 2% of global revenues every year to fraud. That may not sound like a lot, but considering that global telecoms revenue was more than $1.5 trillion in 2020, the losses are pretty significant. With the average home having around 25 connected devices and eSIM offering the ability to swap services easily, fraud is evolving. It’s creating more security breach opportunities than ever, and fraudsters strike ninety percent of communication service providers (CSPs) daily. Traditional rule-based fraud prevention can’t keep up with fraudsters ever-changing strategies, and the change in customer-activations behavior thanks to the restrictions of a pandemic has also made it more difficult to identify fraudsters, further increasing risk.
So what's a CSP to do? In this case, turn to artificial intelligence.
Amdocs has been working with Bell Canada, who wanted to detect changes in fraudsters' behavior and identify customers at risk of committing fraud much more quickly. Importantly, they needed to be able to distinguish fraudsters from legitimate customers. The innovative solution they deployed uses AI and machine learning – through self-learning and auto-tuning capabilities, the model automatically adapts to learn the constantly-changing behavior of fraudsters and improve over time.
"By using machine learning, we can detect changes in usage. We can immediately learn from it and create models to cope, "says Dr. Gadi Solotorevsky, CTO at Amdocs cVidya. "And with AI, you find things you didn't expect."
The results speak for themselves. Bell Canada had a 10% increase in fraud detection, a 150% improvement in time it takes to detect losses to fraud, and a 200% improvement in the time required to identify new fraud.
"Half of our total fraud losses can now be detected three times faster," says Bell Canada. "Plus, we have reduced the volume of false positives, cutting the time it takes to detect fraud directly reduces our losses."
Are you attending MWC Los Angeles? If so, then you’ll get the chance to find out more because Bell Canada's Alexandre Girard, Senior Manager, Fraud Control & Detection will be discussing Bell Canada's advanced approach to fraud management with Amdocs CVidya CTO Dr. Gadi Solotorevsky during the Disruptions in Data session at 3:00 pm EST, Tuesday, October 26. A case study will also be posted in the weeks to come.