Artificial Intelligence

How Genpact’s AI and predictive analytics helped a Formula E racing team finish in the top 3 all season

  • AI and predictive analytics are being applied with positive results to Formula E racing.
  • Genpact's Armen Kherlopian joins us to discuss how this applies to financial services.
close

Email a Friend

How Genpact’s AI and predictive analytics helped a Formula E racing team finish in the top 3 all season

What does car racing have to do with financial services? Actually, a lot. Many of the same dynamics persist — improving car and driver performance, optimizing operations and sustainability. Substitute financial performance, personalized product marketing, and risk management and now you’re talking about financial services. Can you identify patterns that provide better competitive insight and winning race strategies?

Just as Moneyball revolutionized baseball, AI and predictive analytics are transforming Formula E racing. Formula E, by the way, has similar cars as Formula 1, but they’re electric. Richard Branson’s Envision Virgin Racing team approach professional services firm Genpact to see if it could improve the team’s performance. Genpact's Chief Science Officer Armen Kherlopian joins us on the podcast to discuss how his team’s advanced analytics solutions and race strategies helped keep the racing team in the top three all season.

Importantly, we talk about how this work can be applied to financial services and the role AI and predictive analytics tools will increasingly play for competitive firms.

SubscribeiTunes I SoundCloud I Spotify
The following excerpts were edited for clarity.

Formula E and predictive analytics

Formula E is similar to Formula 1 but the engines are electric. The locales are similar in Hong Kong, Santiago, Berlin and New York City. You know, without the roar of the engines, the race is very close to the audience.

Over a year ago at the AI Summit in London, the Envision Virgin Racing team -- Sir Richard Branson's team -- approached us. They asked if we could get the team to go faster, further and safer.

There's an intriguing dynamic with electric car racing. Unlike other races where you have a set distance like the number of laps, in Formula E, it's time boxed -- 45 minutes plus one lap. When a driver starts the race, he doesn't know how far he has to go, so the racing comes down to driver talent and how strong the algorithms are that we provide.

We have a set of workstreams. We're enabling strategy around overtake -- a risk-adjusted return on energy usage. We advise our drivers Sam Bird and Robin Frijns about how and when to defend together and overtake together.

How to win in Formula E

Given our work across industry areas, we first saw this as a critical resource optimization challenge. How do you get the most out of something that's constrained, the battery? We approached this the same way we would approach capital allocation for a bank's marketing campaign in commercial analytics. We used optimization math and deep learning, extracting additional value from data to make the team competitive.

The interface of AI systems

We consider image, text, regulations, social media and signals across the network of drivers. We roll all of this up in an AI system we developed for the team which is all about action. Interface is key -- in this case, the race engineer tells the drivers to overtake, defend strongly, or go all out. These instructions are data driven. Interfaces have to be use case specific -- whether it's customer service, a race car or product launch. In this case, it's the critical link.

Results of predictive analytics on the racing

Both of our drivers finished the race season strongly. Our Dutch driver took first position in the finale race. Output is measured in wins and points. We're among the best. We believe we've sparked a bit of a software war now to match our team's algorithm capabilities.

It's like Moneyball for racing. I had a brief exchange with Billy Beane over the past few weeks. It's part of a broader trend, whether around capital markets, financial services, or consumer banking. What it means to be data driven involves a new sophistication of algorithms but also some cultural aspects.

The parallels between racing and financial services

The ability for an organization to acquire and service customers is paramount. The time scales are compacting. In racing, it's acute. The difference between doing an overtake or not mean the difference of standing on the podium or not. In consumer banking, this means getting marketshare and understanding customers.

This ties back to culture -- customers expect relationships with their financial organizations that are personal and not cookie cutter. It all comes back to data.

Who wins in this new world

Organizations have to be very serious about AI and analytics and what it means for digital strategy. If we look back at the industrial revolutions, electricity spawned innovations in and across industries. The internet did something similar. The pattern detection of AI looks to be a third major trend.

Algorithms require strong leadership

Companies will need to partner or develop in-house capabilities. Even better, they should build ecosystems that relate to their business model -- it can be about data use, go to market, or enhancing the customer experience. Being serious about algorithms is important. But culture and courage are absolutely essential.

We're going to see that companies that say they are data driven will be tested because sometimes insights are counterintuitive. With the race team, we found key patterns around specific turns that were unintuitive to the team that they embraced that lead to better performance. That's really what good leadership is all about: to take an insight and to drive it to an action. For a bank or fintech, it's about a hypothesis not about where the market is, but where it's going.

0 comments on “How Genpact’s AI and predictive analytics helped a Formula E racing team finish in the top 3 all season”

Artificial Intelligence, Green Finance, The Green Finance Podcast

The Green Finance Podcast Ep. 15: Why climate AI is essential to reach net zero

  • Today, we're talking about artificial intelligence – a tool uniquely positioned to help manage the complex issues presented by climate change.
  • To help us understand more about how AI can help us solve the climate crisis, I've invited BCG's leading sustainability expert Mike Lyons to expand upon the study findings and explore real-world, practical applications for climate AI.
Iulia Ciutina | December 09, 2022
Artificial Intelligence, Member Exclusive

Deep Dive: What’s in the black box? The challenges of explainable AI in digital finance

  • In the wake of reports of discrimination and negative impacts on consumer wellbeing, regulatory scrutiny is increasing on FIs that use AI models.
  • AI is central to digital finance – but do we understand how it truly works?
Rabab Ahsan | November 14, 2022
Artificial Intelligence, Sponsored

How financial institutions can get the most out of artificial intelligence

  • Artificial intelligence is a complex technology with a variety of applications. For best results, financial institutions should implement AI with a specific need, plan, and strategy in mind.
  • AI can help financial institutions move beyond a transactional, generalized digital banking experience, and deliver branch-like banking on digital channels at scale.
Finalytics | November 07, 2022
Artificial Intelligence, Data

‘This year, banks will strive to balance two opposing forces’: The state of AI in banking 2022

  • AI developments in banking have so far been restricted mostly to back-end uses. This year, there is a desire among service providers to focus on innovating more for the front-end.
  • As AI becomes smarter and banks begin holding increasingly intimate data about their customers, the industry is expected to progress slowly and responsibly.
Subboh Jaffery | January 31, 2022
Artificial Intelligence, Sponsored

Four ways we can ensure AI lending works for everyone

  • Real competition in credit scoring and rigorous fair lending testing for all players will help expand credit access
  • Built correctly and with care, AI models can be even more transparent than legacy scores, which have yet to undergo real public scrutiny of their disparate impact
Zest AI | December 14, 2021
More Articles