R03 — JAPANESE GRAND PRIX

Mercedes 1-2 in Japan

41%

Our model estimates a 41% probability for this prediction, based on the analysis of multiple factors and Monte Carlo simulations.

41%Mercedes 1-2 in Japan
15%41%29%

41% [15%29%] (95% CI)

01 / KEY FACTORS

Impact by factor

Recent form
+5.5%
Constructor advantage
+4.4%
Historical record
+3.9%
Variance
-2.6%
Conditions
-2.1%
Impact total+9.1%
02 / MONTE CARLO SIMULATION

Distribution and quantitative analysis

10,000 simulations Monte Carlo

Position Distribution

10,000 simulations

Distribution Statistics

N Simulations10k paths
ExpectedP3.1
MedianP2
ModeP2
Std Dev2.14
Skewness+1.93 →
VaR 95%P7
CVaR 95%P8.7
Prob(P1)22.0%
Prob(Podium)70.0%
Prob(Points)98.9%
Prob(DNF)5.0%

Convergence

Scenario Analysis — Mercedes 1-2 in Japan

ScenarioPositionProb.Conditions
Best case (P5)P122%Clean qualifying, optimal tyre strategy, no safety car disruption
Optimistic (P25)P116%Strong qualifying, competitive race pace, favourable pit window
Base case (P50)P112%Average qualifying, standard strategy, representative race pace
Conservative (P75)P37%Suboptimal qualifying, traffic in DRS zones, one extra pit stop
Worst case (P95)P62%Safety car at wrong time, poor start, high tyre degradation

Sensitivity Analysis

03 / FEATURE ANALYSIS

Variable analysis

Base value5.0%
Output41%
5.0%
41%
primary_factor+5.5%
constructor_rank+4.4%
historical_data+3.9%
model_uncertainty-2.6%
external_conditions-2.1%
Feature importancei
primary_factor
0.155
constructor_rank
0.132
historical_data
0.115
recent_form
0.098
external_conditions
0.082
model_uncertainty
0.068
reliability
0.055
teammate_delta
0.042
strategy_factor
0.035
weather
0.025
Feature correlationsi
form_score
constructor
quali_pace
circuit_hist
tyre_deg
reliability
form_score
constructor
quali_pace
circuit_hist
tyre_deg
reliability
-1.0
0
+1.0
04 / MODEL VALIDATION

Model performance

Model performancei
Accuracy0.720+0.240 vs baseline
Brier Score0.041-0.006 vs baseline
Log Loss0.770
AUC-ROC0.800
Calibration curvei
0%0%20%20%40%40%60%60%80%80%100%100%PredictedActual
Confusion matrix
Predicted vs Actual72% accuracy
Yes
No
Actual
Yes
14
6
No
5
12
Pred.
Track characteristicsi
Top SpeedDownforceTyre WearBrakingOvertakingPU Demand

Accuracy

72%

across 127 race winner predictions

Average Brier score

0.041

probability calibration

Last correct

Australia R1

Australia R1

05 / CIRCUIT ANALYSIS

Circuit factors

Suzuka history

Last 3 races

2023

P3

2024

P2

2025

P4

Practice pace

Gap to leader (sec)

RUS
REF
NOR
+0.3s
LEC
+0.5s

Tyre degradation

Lap time, laps 1-20

Lap 1Cliff ~L12Lap 20
06 / EVOLUTION & DATA

Probability over time

Training Data Sample4 rows x 5 cols
#seasoneventresultprobabilitycorrect
12025R1Yes52%Yes
22025R2No38%Yes
32024R1Yes45%No
42024R2No62%Yes