Reference

Models Reference

How the intelligence is built. Fourteen production ML models, plus an algorithmic layer (CTMC win/podium probability with a full position distribution, ECP/ECPA expected championship points, and EKF tyre health), produce the analytics.* and weather.* feeds. This page documents how each model works — its type, inputs, and calibration. For the payload each one emits, see the Analytics feeds →

Models are delivered as feed outputs, not as a separate product. You subscribe to a feed (e.g. analytics.strategy); the models behind it run server-side in real time. The model count is the documented source of truth; the live GCS manifest is the runtime truth.

Production ML models

ModelTypePredictsFeed
pit stop probabilitygradient-boosted-ensembleP(this driver pits this lap), every lap.analytics.strategy
safety cargradient-boosted-ensembleP(SC or VSC deployment next lap), session-level.analytics.strategy
overtakegradient-boosted-ensembleP(position gain via on-track overtake within 3 laps), per driver.analytics.strategy
LTOE lap-time outlier estimationgradient-boosted-ensembleLap Time Over Expected — the normalized pace delta, per lap.analytics.strategy
tyre cliffgradient-boosted-ensembleP(tyre performance cliff), per driver per lap.analytics.strategy
undercut threatgradient-boosted-ensembleP(an undercut attempt against the car ahead succeeds), when in range.analytics.strategy
undercut timing callcalibrated-classifierWHEN to strike: the recommended undercut lap and its success probability.analytics.strategy
overcut threatgradient-boosted-ensembleP(staying out longer beats the car ahead's stop), when in range.analytics.strategy
qualifying pacegradient-boosted-ensemblePer-sector pace deltas vs the session median, per driver.analytics.qualifying
fastest lapgradient-boosted-ensembleP(this driver sets the session's fastest lap).analytics.race-odds
DNF risksurvival-modelRetirement hazard per driver, per lap.analytics.strategy
tyre compoundgradient-boosted-ensembleThe next compound a pitting driver takes, as probabilities.analytics.tire-strategy
pit-stop countgradient-boosted-ensembleP(one / two / three+ stops) for the whole race, per driver.analytics.strategy
pit-window survivalsurvival-modelLaps until each driver's pit window opens.analytics.pit-window

Every model has its own page — click a name. All share the training and calibration pipeline below.

Algorithmic intelligence layer

Three non-ML components ship alongside the models and produce the bulk of the race-odds and tyre signals.

Win probability — Monte Carlo

A forward Monte Carlo race-to-finish simulation produces a full 20-element positionDistribution per driver, from which podium/points odds, expected points, expected laps led, and forward position-change projections are derived analytically. Powers analytics.race-odds and analytics.team-points (via joint-distribution convolution).

Tyre health — EKF

An extended Kalman filter tracks each driver's lap-delta series to estimate pace.tyre.health (0–1), degradation rate (s/lap), and stint lap — robust to safety-car and traffic noise that fools a naive regression.

Expected championship points — ECP/ECPA

Season-level points expectation (and an adjusted variant) projecting championship outcomes from the current standings and per-race position distributions. Surfaces on analytics.championship-probability.

Calibration

Every classifier ships with a calibration stage fitted on held-out sessions, so a published 0.30 means 30%. Models retrain automatically as race weekends land in the pipeline. Live calibration status per model — meeting target, recalibrating, or not yet tracked — is available at the model manifest endpoint, deliberately as a qualitative status rather than a raw metric — self-reported accuracy numbers are easy to publish and hard to verify. The free tier replays this season's sessions, so you can score the projections against what actually happened yourself. That's the stronger signal.

2026 regulation adjustments

The 2026 F1 regulations — tripled ERS power, turbo lag, active aero replacing DRS — required every model to be re-assessed. What changed:

ModelFeedStatusAction taken
Tyre degradationanalytics.strategyRecalibratedCircuit parameters updated for new thermal loading from turbo lag. Wider confidence intervals until 4+ 2026 races.
Win probabilityanalytics.race-oddsUpdatedMonte Carlo pass-through rates recalibrated for the 2026 electric boost profile.
Pit stopanalytics.strategyAdjustedERS clipping creates saw-tooth lap-time variance that mimics cliff signatures. Decision threshold raised for the new variance profile.
Safety caranalytics.strategyOffset appliedBase SC rate offset upward for the first 6 races of 2026 (driver adaptation period).
Overtakeanalytics.strategyRecalibratedCircuit overtake indices updated for zone-independent Overtake Mode vs. DRS-zone activation.
LTOEanalytics.strategyActiveShipped with an early-season damper that lifts automatically once 3+ races of 2026 data exist — lifted for the 2026 season.
← Analytics feedsAPI Reference →