AI Verdict
Away Win — 51% probability ★★★★☆
- J. Reynolds (Sporting Kansas City) — Injury Muscle
- Diego Borges (Sporting Kansas City) — Injury Muscle
- T. Calheira (Sporting Kansas City) — Injury Ankle
Confidence: Decisive · Updated: Thu, Aug 20, 2026 08:00 AM
AI Prediction
Predicted outcome: Away Win (28% probability)
- Home Win: 28%
- Draw: 21%
- Away Win: 51%
Most likely scores: 1-1 (12%), 1-0 (11%), 0-1 (11%)
Model Confidence
Confidence Rating: Decisive (65%)
Clear separation between top 2 outcomes
Prediction Evolution (10 snapshots)
- 17:10 — Home 0% / Draw 0% / Away 0%
- 17:10 — Home 0% / Draw 0% / Away 0%
- 17:10 — Home 0% / Draw 0% / Away 0% (Δ Away -0.1%)
- 17:10 — Home 0% / Draw 0% / Away 0%
- 08:07 — Home 42% / Draw 24% / Away 34% (Δ Home +41.9%, Draw +24.0%, Away +33.3%)
- 08:07 — Home 42% / Draw 24% / Away 34%
- 08:07 — Home 42% / Draw 24% / Away 34%
- 08:07 — Home 42% / Draw 24% / Away 34%
- 08:07 — Home 42% / Draw 24% / Away 34%
- 08:07 — Home 42% / Draw 24% / Away 34%
Advanced Details
Match Signals
- 🩹 J. Reynolds (Sporting Kansas City) — Injury Muscle ✅ confirmed
- 🩹 Diego Borges (Sporting Kansas City) — Injury Muscle ✅ confirmed
- 🩹 T. Calheira (Sporting Kansas City) — Injury Ankle ✅ confirmed
- 🩹 C. Durkin (St. Louis City) — Injury default ✅ confirmed
- 🩹 Celio Pompeu (St. Louis City) — Injury Knee ✅ confirmed
- 🩹 R. Burki (St. Louis City) — Injury Thigh ✅ confirmed
Frequently Asked Questions
- Why is Away Win the clear favorite?
- The AI model assigns 51% probability to Away Win, indicating strong confidence based on historical data, ELO ratings, and recent form analysis.
- What is the biggest factor affecting this prediction?
- J. Reynolds (Sporting Kansas City) — Injury Muscle
- How confident is the model in this ranking (Decisive, 65%)?
- Model Confidence measures how certain the AI is about the order of outcomes, not any single probability. A clear gap between the top two outcomes gives the model high conviction in its ranking.
- How does the AI prediction model work?
- Our ensemble combines Gradient Boosting and Random Forest models trained on historical match data, ELO team ratings, recent form, and statistical metrics. Score distributions use Poisson-based simulations for the most likely scorelines.