Podcast Audio Transcript
Alisha: Hello listeners, this is Alisha; thank you for tuning in to yet another exciting and informative podcast from us at Infosys BPM. Today, we are discussing about telecom fraud management with signalling solutions. And to talk about this, we have here with us, Anand Chandrashaker, Senior Domain Principal – Digital Transformation Services. Welcome Anand. How are you?
Anand: I’m doing great, Alisha. Nice to be back in this podcast.
Alisha: It’s always a pleasure to have you.
When we are looking at new-age telecom services, they have become quite complex with the advent of 5G, fibre, and cloud. In this complex ecosystem, how significant is the fraud and revenue leakage problem?
Anand: Yes, it’s quite a relevant question Alisha. Telecommunication is one of the most rapidly growing sectors today with all those technological advancements you mentioned. As the technological wizardry and complexity of the processes increase, so does the possibility of fraud and revenue leakage. This is more so because telecom customers are receiving more advanced services these days.
Revenue leakage, as you might imagine, is an unintended and unnoticed loss of revenue. When we examine the causes of this leakage, the top ones include inefficient processes, technical configuration issues, order management issues, and unformatted records.
Fraudsters intentionally use various ways to inflate, divert traffic, and make money in the form of commissions from “grey routes”, which exploit the vulnerabilities of telecom networks, and in turn incur losses for telecom operators.
These issues cause telecom companies to lose around 2-5% of their total revenue. That means, with the current telecom industry size of around 2.8 trillion dollars, revenue leakage could touch at least 30 to 40 billion dollars.
Alisha: That’s indeed a hefty loss for communications service providers.
How do you propose to improve fraud management for telecom companies?
Anand: Revenue assurance involves ensuring that all products and services provided by telecom companies are billed as per the commercial agreement with customers, by ensuring this billing. Besides this, configuration integrity and accuracy across the relevant systems should be ensured. Teams should continuously monitor process flows to plug gaps and assure revenue, and also to prevent fraud.
Today, revenue assurance and fraud management teams use MS Excel, SQL, big data, and Hadoop platforms to write queries and identify issues and outliers; they then highlight these issues to technical teams to resolve them.
Here the problem is, most of the issues are identified after the fraud or revenue leakage has occurred. So, teams are scrambling to control the damage and put in methods and processes to ensure that the issue is not repeated. So, it’s evidently a reactive process. Based on the time taken to identify the issue, some revenue is always lost.
Alisha: So, you mean to say that this traditional solution is not real-time.
Anand: Exactly.
The catch here is that it takes a few hours for a call data record to eventually reach the fraud management system and get analysed after an alarm is triggered.
Hence, in a traditional fraud management methodology, which is reactive, a CSP loses revenue as the fraudulent traffic is not prevented in time. Reporting has its own life cycle and frequencies, so there will always be a delay in identifying issues. It is also observed that controls are not effective with the increase in data flow and increased data processing times.
Alisha: So, Anand, if the traditional approach is time-consuming and less effective, what is a better solution for this?
Anand: Alisha, rather than a rule- and report-based solution, a signalling-based solution can be more effective for efficient network fraud detection. Let me elaborate.
In signalling-based fraud management, the issues are identified based on the call location, device IDs, and protocols used, among others. So, the issue can be identified prior to the completion of the call, and we don’t have to wait for a report.
The signalling solution makes fraud management both predictive and preventive, when the delay in data loading and reconciliation are addressed. And fraud management is done on the basis of signal data and a set of rule-based algorithms. With this, we can prevent leakage as well as frauds from happening in the network, and thus assure revenue.
If we look at the hard numbers, signalling-based solutions can give at least 30% improvement from the current fraud management models.
Alisha: Yes Anand, that sounds like a better solution for this pain point faced by CSPs.
Thank you for your inputs on this topic and for your time in our podcast today.
Anand: It’s always a pleasure Alisha. Thank you for having me.
Alisha: Dear listeners, if you enjoyed our podcast today, please don’t forget to share and like it on social media. Our social handles are mentioned in the podcast page. The podcast will be available on various platforms like Google Podcasts and Spotify, in addition to our website.
Also, if you have any queries, do reach out to us through the email address on the podcast description. Watch this space for more exciting podcasts coming up. Once again, thank you for tuning in, stay safe, sharp, and healthy. Have a nice day!