Crossing data and AI: The Genpact and Envision Racing story

The FIA Formula E Championship is the world's most disruptive motorsport series where drivers race cutting-edge electric vehicles to razor-thin victories. By demonstrating the cars' power on the track, Formula E is building a fan base that also embraces having electric vehicles on the streets, reducing pollution and combating climate change.

But it's not only the series that's innovative. Formula E is also witness to the evolution of the world's first instinctive racing team, the result of a unique partnership between Genpact and Envision Racing. By bringing together the race team's engineering expertise with our data-science skills, we're improving collaboration, generating predictive insights, and enabling a more adaptive workforce.

With our shared focus on using data for competitive advantage, we've enhanced Envision Racing's ability to make lightning-fast decisions for superior performance.

The sporting world is increasingly data-driven, especially in racing, where a hundredth of a second can be the difference between winning and losing. Envision Racing is one of the most recognized and successful teams in this disruptive championship. As a founding Formula E team, it has long focused on combining outstanding drivers and expert engineering with technical innovation.

Entering the 2018-2019 Formula E season, Envision Racing faced several changes to the rules and new challenges that fundamentally reshaped the team's approach to each race:

• Races changed from a fixed distance to a timed race of 45 minutes plus one lap, making accurate energy management mission-critical
• The introduction of a mandatory “attack mode" race element gave drivers an extra boost of energy. Each team must decide when to use it to gain competitive advantage
• The new Gen2 car's extended battery life eliminated the need for pit stops to change cars mid-race
• The addition of a new team added two more cars to an already competitive field

Even with world-class drivers and an expert engineering and support team, Envision Racing saw the need for greater competitive advantage. Because data is so crucial to success, it sought a partner that could help enhance race-day performance by gaining greater insights at the right time using AI and analytics.

The team knew it had to accelerate and sharpen decision-making to improve energy management. One priority was the ability to accurately predict the number of laps left in any given race while taking into account thousands of variables. In addition, the team wanted to better understand its drivers' strengths and weaknesses on each circuit, and gain more detailed competitive intelligence.

With our experience and skills in digital technologies, including AI and advanced analytics, we worked to help Envision Racing make fully informed, winning decisions, at speed.

In the first season of our multi-year partnership, we focused on three key areas:

Operations optimization – transforming race operations with accurate predictions

Building peak performance – uncovering detailed driver insights from simulator data

Alternative data analysis – using an untapped source of data to create profiles on competitors

To optimize operations, we addressed the uncertainty of the timed race. We designed the Lap Estimate Optimizer (LEO), an AI-powered scenario engine, to quickly and accurately predict the number of laps in a race. LEO assesses in real time how thousands of possible race situations – such as adverse weather, crashes, red flags, changing track conditions, and more – can impact the total number of laps remaining in a race.

With the predictive insight of knowing how many laps are still ahead at any moment in the race, the team can decide how best to approach turns and overtakes, when to use attack mode, and how to balance speed and battery consumption.

The team has found that LEO can predict the lap numbers ahead of its more classic methods and works particularly well in the extreme weather conditions drivers often face. In Paris, for example, where it rained – and hailed – and in Santiago, a very hot race, LEO settled on the right number many laps earlier, providing a huge advantage.

LEO's benefits go far beyond a Formula E city track. Think of a consumer goods company, for example. With accurate predictions, it can make real-time decisions on market demands that reduce costly stockpiles and delivery delays. Such an agile supply chain can adapt to every scenario.

To build peak performance, Genpact analyzed the data from hundreds of pre-race simulator runs that drivers Sam Bird and Robin Frijns undertake as part of their preparation. These insights reveal their strengths on the track so that they can learn from each other and make the most of their collective abilities.

In the season's closing race in New York City, insights from the previous race combined with the drivers' simulator data showed the team the path to victory. Armed with fresh analysis, Robin knew when to get the best use of attack mode and overtook his rival to secure the win. By combining insights from multiple sources, the team continues to grow stronger with every race.

Genpact uses the same peak performance approach to help businesses manage large-scale change initiatives. Companies improve outcomes, enhance the customer experience, and reduce costs by capturing and analyzing data from one project phase to the next.

The third solution comes from our ability to draw insights from alternative data sources, such as GPS and radio. By cleansing and analyzing publicly available GPS race data, for example, we can create heat maps that reveal rival drivers' tendencies on the track. Race strategists can then identify the drivers who are likely to over-consume energy and how they might behave on different parts of the circuit, giving the Envision Racing drivers a decision-making edge.

Businesses across industries can benefit from this approach, too. Insurers, for instance, rely on large pools of data from many sources to make the right claims decisions. By using AI to analyze millions of auto-damage images, insurers' customers get almost real-time estimates on repair costs and swift claims decisions.

Over 13 races in 12 cities, Genpact's data expertise has helped Envision Racing make real-time decisions that have enhanced performance and contributed to six podium finishes and a third-place finish in the team championship overall.

Our work together has revealed important lessons in digital transformation for race teams and Fortune 500 companies alike:

1. AI doesn't replace people. Quite the opposite. AI augments a team's industry, processes, or expertise, and can't exist without them. Insight from data relies on the judgment and context that only people can provide
2. With augmented expertise, it's not just about increasing the volume of insights but also their accuracy and timing so that you can act on them when you need them
3. Embed data and analytics in your company's genes. To stay competitive, embrace upskilling across your organization
4. Generating predictive insights alone is not enough. Teams must be able to easily and quickly access and digest them, and then act
5. Nurture a team of teams with broad expertise – both internally and with partners. A connected ecosystem that collaborates effectively to produce relevant, seamless solutions

Building on all these lessons, Envision Racing's drivers and strategists now have tools that enhance their forward-looking decisions.

Through extreme heat, aggressive competition, a hailstorm, and nail-biting finishes, Genpact and Envision Racing are mastering how to stay ahead. And as our collaboration brings success to the racetrack, we're taking what we've learned to boardrooms, helping ambitious businesses so that they too can transform at the speed of instinct.