R03 — JAPANESE GRAND PRIX
Russell wins the Japanese Grand Prix
41%
Our model gives George Russell a 41% chance of winning the Japanese Grand Prix, based on 28 features and 10,000 Monte Carlo simulations. Mercedes have won both races so far in 2026 with consecutive 1-2 finishes.
41%Russell
22%41%35%
41% [22%–35%] (95% CI)
01 / KEY FACTORS
Impact by factor
R01-R02 results (P1, P2)
+9.1%
Mercedes constructor lead
+7.2%
Qualifying pace (2 poles)
+5.8%
WDC leader (51 pts)
+4.9%
Suzuka high-downforce suits W17
+3.5%
Antonelli teammate threat
-3.2%
Weather uncertainty
-1.5%
Impact total+25.8%
02 / MONTE CARLO SIMULATION
Distribution and quantitative analysis
10,000 simulations Monte Carlo
Position Distribution
10,000 simulationsDistribution Statistics
N Simulations10k paths
ExpectedP2.9
MedianP2
ModeP1
Std Dev2.13
Skewness+1.97 →
VaR 95%P7
CVaR 95%P8.7
Prob(P1)28.0%
Prob(Podium)72.3%
Prob(Points)99.0%
Prob(DNF)5.0%
Convergence
Scenario Analysis — Russell
| Scenario | Position | Prob. | Conditions |
|---|---|---|---|
| Best case (P5) | P1 | 28% | Pole position, clean start, optimal medium-hard strategy at Suzuka |
| Optimistic (P25) | P2 | 22% | Front row start, competitive race pace, Mercedes 1-2 again |
| Base case (P50) | P3 | 16% | P2 qualifying, Antonelli takes the win, Russell holds off Ferrari |
| Conservative (P75) | P5 | 8% | Qualifying error, traffic in Suzuka S-curves, suboptimal pit window |
| Worst case (P95) | P8 | 3% | Rain disruption, safety car negates pit strategy, high tyre degradation |
Sensitivity Analysis
03 / FEATURE ANALYSIS
Variable analysis
Base value5.0%
Output41%
5.0%
41%
recent_form_score+9.1%
constructor_advantage+7.2%
qualifying_pace+5.8%
wdc_position+4.9%
circuit_aero_demand+3.5%
teammate_threat-3.2%
weather_risk-1.5%
Feature importance
recent_form_score
0.152
constructor_advantage
0.138
qualifying_pace
0.122
wdc_position
0.108
circuit_aero_demand
0.095
teammate_performance
0.082
tyre_degradation_rate
0.072
weather_risk
0.058
pit_stop_efficiency
0.045
overtaking_difficulty
0.035
Feature correlations
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 performance
Accuracy0.780+0.230 vs baseline
Brier Score0.041-0.006 vs baseline
Log Loss1.856
AUC-ROC0.842
Calibration curve
Confusion matrix
Predicted vs Actual78% accuracy
Track characteristics
Accuracy
78%
across 127 race winner predictions
Average Brier score
0.041
probability calibration
Last correct
China R2
China R2 — Russell P2
05 / CIRCUIT ANALYSIS
Circuit factors
Suzuka history
Last 4 races
2022
P8
2023
P4
2024
P3
2025
P2
Practice pace
Gap to leader (sec)
RUS
REF
ANT
+0.2s
LEC
+0.6s
HAM
+0.7s
Tyre degradation
Lap time, laps 1-20
Lap 1Cliff ~L12Lap 20
Lap time distribution
Russell
Antonelli
Leclerc
Hamilton
91.0s92.0s93.0s94.0s
06 / COMPARISON
Russell vs Antonelli vs Leclerc
Russell
Antonelli
Leclerc
Qualifying pace
94
90
82
Race pace
92
88
80
Circuit history
72
20
78
Reliability
95
95
85
Recent form
96
94
78
Head-to-head
| Driver | Quali avg | Race pace | Finishes | Podiums | DNFs |
|---|---|---|---|---|---|
| Russell | 1.5 | 1:31.8 | 2 | 2 | 0 |
| Antonelli | 1.5 | 1:32.0 | 2 | 2 | 0 |
| Leclerc | 4.0 | 1:32.6 | 2 | 1 | 0 |
| Hamilton | 3.5 | 1:32.5 | 2 | 1 | 0 |
07 / EVOLUTION & DATA
Probability over time
Training Data Sample5 rows x 8 cols