How we predict
We do not pick winners. We assign probabilities. When we say a driver has a 28% chance of winning, we mean that across many similar situations, that outcome would occur roughly 28% of the time.
Our system connects directly to primary F1 data sources, engineers 52 predictive features, fuses four distinct signals (Elo, ensemble model, recent form, team performance), and runs 10,000 Monte Carlo simulations. Every prediction is published before the race and scored after.
Primary Data
We connect directly to primary F1 data sources. No third-party API dependencies. Every data point is traceable to its origin.
- F1 Live Timing (real-time telemetry)
- formula1.com (official results)
- FIA (stewards decisions, regulations)
- Historical archive (1950 to present)
Feature Engineering
Raw session data is transformed into 52 predictive features for each driver-race combination.
- Qualifying pace
- Race pace & tyre degradation
- Circuit history
- Weather conditions
- Safety Car probability
- Constructor development trajectory
Model Inference
An Elo rating system combined with recent form and team performance generates calibrated probabilities, validated by 10,000 Monte Carlo simulations.
- Elo ratings with regulation resets
- Recent form + team car performance signals
- Monte Carlo simulation (10,000 paths)
- Dynamic weighting as season data grows
Race Winner
Win probability for each driver, combining Elo ratings with recent form and car performance
Podium
P(podium) for each driver via Monte Carlo position distribution
Safety Car
Probability of Safety Car, VSC, or red flag during a race
Monte Carlo
10,000 race simulations producing full position distributions and expected points
Championship
Season-long points simulation and title probability
Calibration
Probability calibration and scoring against standard baselines
Every prediction we publish is scored against reality. No cherry-picking, no retroactive adjustments. The full history is public.
What is a Brier score?
The Brier score measures the accuracy of probabilistic predictions. It is the mean squared difference between predicted probabilities and actual outcomes. A perfect score is 0.000. A coin flip on a 20-driver field scores approximately 0.090.
We also compute a skill score: how much better (or worse) our predictions are compared to naive baselines like grid position or championship standings. A positive skill score means our model adds value over simpler approaches.
The same scoring system is used in meteorology, epidemiology, and quantitative finance. It penalises overconfidence and rewards honest uncertainty.
113
Predictions scored
68.8%
Accuracy
0.035
Brier score
Our data infrastructure is fully independent. Zero third-party API dependencies in production. We connect directly to primary sources, ensuring reliability, speed, and complete data traceability.
F1 Live Timing
Real-time telemetry, lap times, positions, race control via SignalR
formula1.com
Official race results, driver profiles, team data, calendar
FIA
Stewards decisions, technical directives, regulations, penalty points
Historical archive
Complete race data from 1950 to present, digitised and normalised
The same methodology, adapted per series. Our architecture is designed to support multiple motorsport championships from a single platform.
Formula 1
Active
Since 1950
Formula E
Coming soon
Since 2014
WEC
Coming soon
Since 1953
IndyCar
Coming soon
Since 1996
WRC
Coming soon
Since 1973