Microsoft Automotive Company newsroom

Mercedes-AMG PETRONAS F1 Team

Real-time Analytics

Mercedes-AMG PETRONAS F1 Team needs to make race-day tire and pit-stop decisions in seconds while accounting for weather, tire degradation, telemetry, and rival behavior; prior simulation turnaround was too slow to support live strategy changes at trackside.

"could take up to an hour, sometimes more"
"those same simulations can take seconds"
"thousands and thousands, if not millions, of these races"

Reported impact

Business outcome

Azure Batch reduced simulation turnaround from up to an hour to seconds, allowing Mercedes strategists to run far more scenarios during live races and support winning in-race calls such as the Miami undercut that helped Kimi Antonelli take the lead.

  • Productivity Improvement
  • Scalability

Solution

Mercedes-AMG PETRONAS F1 Team uses Microsoft Azure Batch to scale race-strategy analytics during Grand Prix weekends. Strategists ingest live inputs including rival-car pace, tire behavior, local weather radar, forecast updates, and each Mercedes driver's telemetry, then run full-race simulations that model every lap, pit stop, and overtake under different tire and weather scenarios. Azure Batch provides burst compute so the team can execute thousands to millions of runs in parallel, both before the race and from the pit wall during Sunday competition, instead of waiting up to an hour for Saturday-night processing. Results are fed back to strategists, who update models live and translate the outputs into concrete tire, pit-stop, and undercut decisions for drivers and pit crew. The source does not name a dedicated storage tier; the described architecture is centered on cloud compute returning decision support in seconds at trackside.

Data flow

Weather radar, forecast updates, rival-car pace data, tire-degradation observations, and Mercedes telemetry are fed into strategy models that simulate complete races. Azure Batch runs thousands to millions of parallel scenarios and returns results in seconds to the strategy team at trackside, where they update models live and convert the outputs into pit-stop and tire calls communicated to engineers, drivers, and the pit crew.

Solution architecture

1 components · 1 layer
  1. Compute
    • Azure Batch Runs large numbers of parallel race simulations so strategists can test scenarios and get trackside decision support during a Grand Prix.

Architecture clues

  • Azure Batch is used to scale compute during live race operations, not just pre-race analysis.
  • Simulation results are consumed directly from the pit wall during Sunday races.
  • The source describes live model updates but does not name a storage platform or data warehouse.
  • The strategy team runs end-to-end race simulations covering every lap, pit stop, and overtake.

Evidence from the source

"Azure Batch has revolutionized our race strategy – scaling thousands of simulations in real time, we can ramp up massive compute during the race so we get… insight when it matters most"
"He goes to his trackside console and assesses the data – from the other cars, from the weather forecasts and from Antonelli’s own telemetry readings"
"In the past, McMillan might run the simulations on a Saturday night while the team was at dinner, which could take up to an hour, sometimes more. Now those same simulations can take seconds and be run from the side of the track"
"Machine learning, as McMillan calls it, has always been a huge part of his job"
"Using Azure Batch, they can run huge numbers of race simulations simultaneously, testing multiple scenarios before, and even during, a Grand Prix"
Transparency Evidence & methodology 75/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value75/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency10/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Microsoft

    How AI is Helping Formula One Teams Win | Signal magazine

    First-party
    https://news.microsoft.com/microsoft-signal/magazine/issue/06/the-winning-formula-formula-one-data-ai-microsoft-interview/
    Source type
    Vendor-published customer story
    Published
    Sep 16, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • Business outcome
    • Metrics
    • Architecture
    • Publication date

Date evidence

  • Published on source page Sep 16, 2026 · Mercedes-AMG PETRONAS F1 Team · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.