Contact Us
  • Case study

Radio analytics: Amplifying a data-powered strategy

Winning insights are in the air. You just need to know how to tune in and listen

"Reduce bias!"

"I don't think that would help!"

"Copy. Grip six, grip six!"

In the heat of a Formula E race, radio communications between drivers and their engineers are critical to success, even if they don't make much sense to the untrained ear.

These exchanges are treasure troves of insights if you can analyze and interpret their vast volumes of information. The partnership between Genpact and Envision Racing, a founding team in the FIA Formula E World Championship, is doing just that.

Radio analytics enhances the team's competitive edge, using technology to quickly unlock insights from teams' communications and respond during the race or feed them into future strategies.

And with the world championship's schedule flexible and subject to change due to COVID-19, the need to turn data into an on-track advantage has been amplified even further. The combination of deep racing knowledge and digital skills could not have come at a better time.

The challenge

The search for timely insights from unstructured data

During every Formula E race, 22 drivers and engineers share details on energy status, strategy instructions, encouragement, and frustrations on the radio. Formula E makes these channels public so anyone can listen in. Some instructions are in code while others are plainly spoken.

Envision Racing has competed in every race since Formula E's inception and is always looking for a fresh source of advantage. The team has known this radio chatter carries significant competitive intelligence. Listening to each unedited audio stream, however, was time consuming and couldn't deliver insights at scale. And there was always other important work for team members to do.

Facing fierce competition, the team needed to arm its drivers and engineers with quality strategic insights and top-tier race preparation. The importance of radio analytics has skyrocketed and Genpact is helping the team meet the accelerated demand for radio insights.

The solution

Automating the listening process

Envision Racing wanted a model to sort relevant clips and then group them by driver and race, enabling engineers to act on conversations faster. But because clips are short and often contain encoded messages, standard algorithms can struggle with them.

The first step was to build a transcription platform that could translate speech to text and automatically eliminate dead air. During a full race session, drivers and their engineers typically speak for less than 10 minutes in total. The team uses this part of the solution in real time.

Genpact designed the Radio Analytics Engine (RAE), a platform that quickly processes each recorded radio stream into relevant clips. Now, nobody has to trim the silence from the audio, and the team can quickly catalog clips by driver and race. This makes it easier to gain quick insights on how rivals approach challenges, including when they may take to the pit, how they manage remaining energy, and when they use attack mode – an extra boost of energy available to all drivers during the race.

By introducing natural language processing to RAE, the team will automate clip sorting quickly enough to access insights and intelligence during a race. With more detailed competitive knowledge, drivers can make better in-race decisions, improve overtaking and defensive strategies, and change the outcome of a race.

See how we unlock insights from radio communications

The impact

Sharpening its edge

These live radio conversations can reveal important insights into the motivations and behavior of each competitor. Because every race is hard to predict, Envision Racing needs to maintain its edge over its rivals.

Gil Abrantes, strategy engineer at Envision Racing shares examples of how RAE is making a difference to the team. “Monitoring competitors allows us to adjust our strategy in real time. If we know when another driver is considering taking attack mode, we can act in advance.

“For example, in Puebla, Mexico, Nick started eighth on the grid. He used radio analytics insights to help decide when to take attack mode and overtake, which contributed toward his third-place finish and first ever Formula E podium."

With technology on hand that accelerates radio analysis, the team has given itself a head start on this vital intelligence-gathering process, especially when there are multiple races over a weekend.

Instinctive racing

See how we're boosting performance for Envision Racing

“The insights from radio analytics make a massive difference. We wouldn't be able to pull such valuable insights from such high volumes of unstructured data at speed and scale without Genpact's skills with digital technologies and data," says Abrantes. “We can now go out on track knowing we've left no stone unturned during our race preparation."

This solution is another component of advanced analytics that will continue to boost driver performance not just with energy management or driver dexterity, but also with the additional power of superior data-led insights.

Faster access to insight on how competitors make in-race adjustments and adapt to changing conditions enhances Envision Racing's pre-race strategy and ability to secure more podium finishes and a coveted season victory.

Read on to see how the technology behind RAE can enhance your business

​From the racetrack to the boardroom​​​

Banking and capital markets

How to improve customer conversations

Live conversations between banks and their customers are still essential to many financial relationships. Yet financial institutions have limited insight into these essential contacts, which can result in missed opportunities or compliance failures.

Speech analytics can examine conversations with customers to help representatives have more productive discussions. The technology can uncover the emotional subtext behind the words, shedding light on customer sentiment and helping banks refine sales messages or improve service quality and the customer experience.


Diagnosing claims early with machine learning

Medical liability insurance protects medical professionals against malpractice lawsuits, but claims are sometimes complex and costly. Lengthy documents and manual processes make adjusting claims expensive and delay the settlement process – increasing the chance of litigation.

We worked with a leading US insurer to apply machine learning to the claims-adjusting process. By extracting claim information from unstructured data, the insurer now has a quicker, more accurate understanding of the potential liability and size of payouts. The insurer can resolve claims faster and avoid expensive litigation.

Consumer goods

Competitive insight sharpens promotional strategies

Every supply chain hides a wealth of insights in unstructured data thought too cluttered or low in quality to analyze in a timely fashion. GPS data on product movement, for example, holds powerful insights that can boost efficiency and reduce supply chain delays.

We're taking on these hidden competitive insights to help consumer goods companies find new pricing and promotional activities while also gaining a better understanding of competitors' strategies.

Life sciences

Patient safety through prediction and prevention

Pharmacovigilance teams identify and track adverse events from medicines, but many face challenges from having to manually process each case. Vast amounts of data from numerous sources are at the root of the problem, made more complex by variations in reporting, language, and formatting.

For a global life-sciences firm, we introduced an artificial intelligence-based solution to extract meaningful insights from both structured and unstructured data, including text and speech. It identifies adverse-event signals and learns in real time to improve future performance. This approach enhances the accuracy and consistency of adverse-event data and reduces effort in case management by 50%.


Turning customer feedback into insights

Manufacturers have more customer feedback channels than ever, but not all have kept pace with the speed and sophistication needed to analyze and harness insights from this data.

We use digital technologies to aggregate and analyze data from social media, customer discussions, trend watchers, and other media sources to uncover emerging market needs and competitor activity. These insights can also show gaps in desired and delivered quality, improve customer satisfaction, and decrease time to market for new products.