Skip to main content
A points-less afternoon can hide a great drive. Hidden performance surfaces those: it compares each driver’s ghost-projected finish what the model expected given their pace in a chosen host car against where they actually finished. A driver who was projected higher than they finished was, in pace terms, under-rewarded by the result.

​
What it shows

The table ranks drivers by the gap between projection and result:
  • Ghost-projected position (fct_ghost_race_finish): each driver’s lap times recombined with a chosen host constructor’s car pace, then re-ranked by predicted mean fuel-adjusted lap pace (not cumulative race time, so a driver who ran fewer laps is not ranked artificially high).
  • Delta: projected minus actual finish. A negative delta means the model projected a better finish than actually occurred the driver was under-rewarded.
  • Confidence: how well the host constructor’s pace is estimated from panel data; more races with that team means higher confidence.
Only scenarios where avg_recombination_confidence ≥ 0.3 are included, and short runs with too few laps for a reliable estimate are excluded.

​
How to use it

  1. Pick a host constructor from the filter bar; projections re-score against that car.
  2. Sort by delta to surface the most under-rewarded drives.
  3. Read confidence before trusting a large delta a low-confidence host pace makes the projection noisier.
  4. Use the self-scenario check as a sanity test: when the host equals the driver’s own team, projected per-lap pace should equal actual per-lap pace. Projected finish position will usually differ from actual finish position.

​
Reading the signal correctly

The delta is pace versus result, not an injustice ledger strategy, safety cars, and incidents legitimately move finishing positions in ways a pace projection cannot see. A negative delta says “faster than the result”, not “robbed”.
When the host constructor equals the driver’s own team (is_self_scenario), the predicted mean lap time (predicted_mean_lap_s) equals the actual mean lap time (actual_mean_lap_s). A gap between those two lap times in a self-scenario row signals a data issue. The projected finish position (predicted_finish_position) does not have to equal the actual finish position (actual_finish_position) in a self-scenario row. The projected finish position ranks every driver in the scenario by mean fuel-adjusted lap pace in the same car. The actual finish position also reflects strategy, safety cars, incidents and retirements. So a non-zero delta_vs_actual_position in a self-scenario row is expected and is not a data issue. On the 2018–2025 build, delta_vs_actual_position is non-zero in about 95% of self-scenario rows (n = 2,786 self-scenario rows that have an actual finish position).

​
Data source

The chart queries fct_ghost_race_finish via DuckDB-Wasm in the browser. The data window covers 2018–2025. For the full model definition, see the fct_ghost_race_finish reference.