- T-Mobile execs explained how they’re using AI to enhance the network
- It’s a model that relies on billions of data points to assess the customer experience across its network
- Is it unique? Perhaps, but other operators also use AI to strategically plot network optimization
For competitive reasons, wireless carriers typically don’t reveal too many specifics about their network expansion and upgrade plans. So when T-Mobile executives were asked during Wednesday’s Q3 earnings call to elaborate on their plans for mid-band 5G upgrades, they steered the conversation to the tools they use to determine how they’re going to expand coverage – as opposed to detailing exactly where and when they will deploy.
Their approach – and brace yourself, this is going to be a real shocker – is based on artificial intelligence (AI). In a nutshell, they’re using “billions and billions” of data points to assess what customers are experiencing across the country. That data gets assigned a customer lifetime value (CLV) and plotted on a grid across the country. Think millions of little hexagons across a map of the U.S.
“We are assigning those values relative to competition to allow us to know exactly where we can build to please customers,” said T-Mobile President of Technology Ulf Ewaldsson. “At the end of the day, this is not a POP drive where you’re just chasing populations and where populations live. It’s a much more complicated art to figure out exactly where customers will value most our build.”
Behind the curtain
It's not the first time T-Mobile has talked about using AI to improve its network.
During the company’s Capital Markets Day in September, Ewaldsson described how they divvy up data sets into what they call these hexagonal pieces of geography that are about 165 meters wide, with even smaller pieces in urban areas. In every one of the “hex bins,” they’re able to study the billions of data points and every single network interaction that occurs in that area.
When there’s a dropped call, weak or imperfect signal, for example, the system can detect that and see if it triggers a call to customer care. That information and more is used to determine what changes, if any, they’re going to make in the network – whether it be the tilt of an antenna or some kind of equipment upgrade.
Ewaldsson described it as transformational in how they think about building and optimizing the network. They are able to understand the value of every dollar they invest and how that translates into customer satisfaction.
T-Mobile CEO Mike Sievert said T-Mobile's approach is different than what many others are doing to prioritize network enhancements.
But it’s not entirely clear how much different it is from rivals’ strategies.
Verizon’s been using AI for network deployment, management and optimization for years, including for coverage optimization. AI is used to establish how Verizon allocates network resources, to forecast energy usage on a cell site level and to answer common language questions about network usage and performance, a spokesperson told Fierce.
AT&T also uses AI tools in its network planning. “We use a mix of traditional and generative AI tools to simulate coverage in different geographies and plan potential deployments. This helps us understand the best places to expand 5G coverage and how to configure our network to optimize performance,” an AT&T spokesperson said via email.
Sizing up the AI strategy
IDC analyst Jason Leigh said he doesn’t know whether T-Mobile’s AI push is unique or if the question that came up during the Q3 earnings call merely gave it a chance to talk about it.
Regardless, it demonstrates that T-Mobile is trying to be more aggressive about using AI. During its Capital Markets Day, Sievert in effect said they were “awash in data” and need to get better at collecting, organizing and interpreting data to drive not only strategy, but day-to-day business decisions and customer engagement, Leigh noted.
“To be clear, operators have used AI for years to manage network traffic and always attempt to leverage data analytics – and maybe AI – for coverage planning and to inform capex strategy. That’s nothing new,” Leigh said. “But Ulf’s comments suggest that T-Mobile is trying to up-level that existing competency in data analysis and interpretation to become even more tactical and surgical in how they leverage data to inform more micro business decisions.”
Recon Analytics’ Roger Entner said what T-Mobile is doing is somewhere between “evolutionary and revolutionary.”
“This is an enhancement to improve what they’ve traditionally done,” he said. “They’re making it better, faster with more dimensions. This is tying a lot more data points together than they typically did.”
“Now they’re going more granular and using more data points. I think it’s a great application of AI and it’s going after one of those lower-hanging fruit," Entner concluded. "It’s the beginning."