At TM Forum Live! (May 15-18, Nice, France), Dr. Roger Brooks, Chief Scientist, Guavus, will take part in the panel debate ‘Leveraging operational and machine intelligence to transform the customer experience’. Here, he discusses his role as Chief Scientist and some examples of the power of intelligent analytics.
Can you tell us about the role of Chief Scientist and why Guavus has hired one?
At Guavus, customers use our products and services, in part, because we offer unique capabilities based on our IP (intellectual property), which is manifested in algorithms and analytics. As Chief Scientist, I am responsible for the latter.
Traditionally, most software companies base their IP on classic computer science algorithms, which pertain to computer architectures, data structures, manipulation and machine usage, etc. This extends to machine learning (ML) where it is often tempting to adopt a “big data” mentality, wherein one starts with whatever data is available and applies various modeling algorithms to see what emerges.
Guavus hired a Chief Scientist not only because of the advanced, highly mathematical nature of analytics needed but, more importantly, due to our approach that provides value to our customers. We use a scientific approach to making decisions based on the data we collect. There is a parallel between a natural scientist’s approach to understanding the natural world and the black box understanding of the systems and users with which we work. We start with scoping insights and actions and later identify the types of data needed and how such data would be observed or collected and subsequently analyzed through ML and intelligence.
Now, sometimes it isn’t that straightforward. Indeed, some of the most interesting discoveries in natural science result from the appearances of anomalies in the analyzed data. Operators need analytics solutions designed to detect and actionably interpret anomalies leading to unexpected insights, which result in cost saving or revenue-generating actions.
Can you share some of what you see as the most inspiring examples of the power of data?
CSPs (communications service providers) need ways to deliver superior customer experiences while reducing their operational costs. This means: 1) Optimizing the efficiency of their network and 2) Reducing the mean time to detect and recover from network issues.
One big way to impact the efficiency of a CSP’s network, for example, is to reduce the number of times a support technician is engaged. Analytics can use knowledge of the system along with the right data to determine if each issue is due to a specific network element or a smartphone/CPE (customer premises equipment) problem. The goal is to uncover and solve issues before the subscriber experiences them. This kind of issue detection, root issue analysis and resolution can save them millions of dollars annually.
Data also helps to reduce the time to recover from network issues. As an arcane example, we are helping one CSP recover quickly from the effects of tropical storms, which are often difficult to predict and can have a devastating impact on the network. By analyzing streaming data, we can identify, in real-time, the optimal locations to deploy repair units. This significantly improves execution in the midst of the vagaries of each storm, increasing service assurance.
Where can data add the most value for CSPs?
CSPs have come to realize the value of analytics. We are now seeing diversity in the use cases, which lead to a definitive ROI. One use case that has risen in popularity over the last few months is network resource optimization. By applying analytics to predict what the network utilization will be at a given time of day, CSPs can determine how best to dynamically deliver high bandwidth consuming applications over their edge networks. This extends the optimizations beyond the reach of CDNs (content delivery networks), for example. For mobile operators, this means that the analytics can pinpoint how subscriber-specific data traffic and radios in RANs (radio access networks) should be managed at any given moment in order to optimize the experiences of all subscribers currently connected to each cell tower.
How is AI (artificial intelligence) delivering value now and looking further ahead, how do you see this evolving?
Today, ML is only as good as the data you use to train it. Machine Intelligence (MI) is the next step and it represents the ability of the machine to extrapolate from raw, disparate data to create new valid information that cannot be discovered by applying a machine-learned model.
For CSPs, the full value of MI solutions goes beyond detecting and prescribing a solution to a problem – it’s about systems becoming intelligent.
Virtual personal assistants and chatbots provide only a façade of intelligence by virtue of the rules they execute behind the scenes. What happens if there is a new phenomenon for which the ML was not trained and the rule or even model not generated? Within the next six to 12 months, MI will be used to infer or extrapolate the kind of issues that an individual subscriber is having based on available data and subsequently be able to share it with the subscriber or customer service agent to help fix the problem. Thus, if a user has an issue with their mobile handset instead of contacting customer care, the system will identify the problem and start a virtual chat or send a message to a customer telling them what the issue is and if there is an action needed (restart the device, etc.), automatically fixing the issue without needing manual intervention from customer service or network operations. In automatically dealing with the number of new and diverse circumstances, the system has no recourse but to act intelligently.
TM Forum Live! takes place May 15-18 in Nice, France. Find out more at www.tmforumlive.org