F1 Race Strategy Decision Support

1.41s

HGB MAE

2,000

Monte Carlo runs

2021–25

Race data

On the held-out rounds, the predicted race-normalized lap-time delta differs from the observed delta by roughly 1.41 seconds on average. This is a lap-time error, not a measure of race-outcome accuracy.

Race strategy couples tyre degradation, pit loss, weather, and uncertainty. Manually reasoning over every combination is impractical, so the system makes the trade-offs explorable.

A simplified processing flow. Each numbered stage feeds the next; storage and retrieval boundaries stay explicit.

1. FastF1 telemetry
2. Feature engineering
3. Rolling split
4. Lap-time model
5. Monte Carlo simulation
6. Strategy bands
7. Interactive dashboard

Predict race-normalized lap delta rather than raw lap time, compare Ridge with HistGradientBoosting, and sample residuals plus pit loss to return P10/P50/P90 strategy-time bands instead of a single false-precision answer.

Wet-weather laps and Las Vegas produce larger errors. The model is more trustworthy in dry-race scenarios and does not yet explicitly simulate traffic, safety cars, or overtakes.

• HistGradientBoosting achieved 1.41s MAE and 2.25s RMSE on rounds 17–24.
• Supports up to 2,000 Monte Carlo simulations per strategy with P10/P50/P90 bands.
• A Belgian GP case study recommended a Medium-to-Hard one-stop comparable to the actual strategy.

Ridge provides the comparison baseline. HistGradientBoosting is evaluated chronologically on rounds 17–24; residual sampling and pit-loss variation produce P10/P50/P90 strategy bands. Those bands describe the simulation assumptions, not every source of race uncertainty.

Build a dedicated wet-weather model, add traffic, safety-car, and overtake effects, and investigate the Las Vegas residual spike.