Why ML-based fraud detection is the way forward for Telco Fraud Management?
The telecoms industry has always suffered from the malicious impacts of fraudsters. In this digital era, traditional telecom services are replaced with new services, giving rise to new fraud types. Therefore, technology to support fraud management operations has changed significantly, with an increased reliance on Artificial Intelligence and Machine Learning as a means for uncovering and identifying fraud. In one of its recent reports, Gartner estimated that by 2022, new implementations of ML within CSP fraud management would reduce fraud losses by 10%.
Will AI/ML be the future for Fraud detection & prevention?
To help us understand this further, it gives us immense pleasure to have interviewed Joseph Nderitu
How has the telco fraud landscape changed in recent years?
There has been significant evolution into new technologies, different access methods, and the proliferation of IP technologies. This means the fraudster may be seated inside the telco premises or half-way around the world and has the flexibility to “hit” the telco in any number of ways. For operators who are offering mobile money, they have suddenly found themselves running a bank on top of their IP network, something that was not in their corporate DNA, so to speak. To cap it all, as we move into the 5G and IoT landscape, the volume of data will be very high whilst the response time to fraud and leakages will be expected to be faster.
Why do telcos need to continuously innovate and invest in newer technologies to address the risks?
The pressure to address risks is higher than ever. Customer expectations are high, and with rising competition, failure to address risk means a reduction in market share. Shareholder value thus gets eroded if risks are not well managed. Regulators are also keeping a keen eye on service providers. This essentially means the challenges are increasing on the one hand, and the service providers’ responsiveness is expected to increase amidst reduced budgets for tools. Innovation is the only way out. We need better tools and methods, which help us to manage risks better.
Do you think AI/ML is the way forward for telco fraud management? And why?
Certainly – if you look at telcos, they are a goldmine of data, always have been. The trends and patterns are there, but we have not been doing a great job of detecting them because the human capacity to see trends is limited. AI/ML technologies remove that limitation – or, at the very least, reduce is significantly. Thus, we are at a sweet spot of sorts – a confluence of rich data, superior ways of looking at the data, and telco businesses that are hungry for insights that will help them manage risks better. As we place everything on IP technologies, it also means we are at a point where the greying of lines between revenue assurance, fraud management, and cybersecurity is happening much faster. The interplay between these areas is a good area for AI/ML.
What are some of the critical fraud areas, which can be covered to a larger extent with AI/ML?
There is a pattern to each fraud. The fact that we do not always do a good job of spotting it with our traditional systems (which are very much rule-based) does not mean the pattern is not there. With that in mind, it means one can apply supervised and unsupervised learning in a lot of areas. There are operators, in Africa, for example, deploying basic learning models on mobile money frauds and using them to identify commission frauds perpetrated in the distribution chain. The features used in such a model would combine the pattern of records obtained from both the GSM systems and the mobile money systems – something that was quite unwieldy to do using conventional FMS. Thus, there is no problem that is too small or too big to be addressed in this new mode of fraud management.
Likewise, with IoT, smarter devices do not mean less fraud, for example – it might just mean an expanded landscape where we (operators and customers) can be hit from any angle.
Does the introduction of AI/ML mean reducing team size, more focus on other areas, and complementing the team with other teams?
There will always be a need for warm bodies. Proper use of AI/ML means we can free human beings to do things that machines still cannot do, or at least cannot do so well. For example, resolving issues still calls for people to talk to each other, negotiate, agree, implement, and track progress. There will always be room for that, so in a sense, and we just need to let the machines do what machines do best and leave humans to do what only humans can do(for now).
While there is a need, are telcos really investing in these technologies?
As always, some will move faster than others. However, regardless of the speed of implementation (which is a function of budgets, organizational politics, and other organizational peculiarities), by and large, this is the direction the telcos are taking. Some are approaching vendors to update tools; others are doing their in-house experiments using freely available resources such as python. All in all, I doubt there is anybody who is sitting with their arms crossed, hoping that the advent of AI/ML is a fad that will pass. The technology is and will keep on evolving, whether we keep up or not.
On-demand Webinar: AI Master Class for Fraud Management
Joseph Nderitu is an independent consultant who specializes in revenue assurance. He previously worked as Head of Revenue Assurance and Fraud Management at Vodacom’s operation in Tanzania, having previously served in the same role at Vodacom Mozambique
Request a demo