How the 2026-08-18 predictions scored against actual results
Cumulative Δlog-loss vs always-pick-home: -0.0266 ± 0.0159 per game over 51 games (paired; negative = beating the baseline - currently ahead).
| Yesterday | Correct | Log-loss |
|---|---|---|
| model | 11/15 | 0.634 |
| always-pick-home | 9/15 | 0.682 |
Daily detail: 73% hit rate · Brier 0.221 · avg margin error 4.1 · avg total-runs error 4.2. Running: 28/51 (54.9%) · cumulative log-loss 0.675 · cumulative Brier 0.241
| Game | Pick | Predicted | Actual | |
|---|---|---|---|---|
| ✅ | Yankees @ Orioles | Yankees (52%) | 4.5–4 | 1–3 (home first) |
| ✅ | Diamondbacks @ Red Sox | Red Sox (59%) | 4.8–4.1 | 9–4 (home first) |
| ✅ | White Sox @ Cubs | Cubs (61%) | 5.2–4.3 | 4–3 (home first) |
| ❌ | Cardinals @ Reds | Reds (50%) | 4.5–4.4 | 0–3 (home first) |
| ✅ | Giants @ Guardians | Guardians (60%) | 4.8–3.9 | 8–1 (home first) |
| ✅ | Dodgers @ Rockies | Dodgers (60%) | 5.5–4.1 | 6–7 (home first) |
| ❌ | Angels @ Astros | Astros (62%) | 4.8–3.8 | 1–3 (home first) |
| ✅ | Athletics @ Royals | Royals (60%) | 5.1–4.4 | 4–3 (home first) |
| ✅ | Mariners @ Brewers | Brewers (62%) | 4.7–3.7 | 22–0 (home first) |
| ❌ | Braves @ Twins | Braves (55%) | 4.9–4 | 4–1 (home first) |
| ✅ | Padres @ Mets | Padres (50%) | 4.5–4.2 | 2–5 (home first) |
| ✅ | Marlins @ Phillies | Phillies (60%) | 4.8–4 | 6–4 (home first) |
| ✅ | Tigers @ Pirates | Pirates (53%) | 4.7–4.6 | 4–1 (home first) |
| ❌ | Blue Jays @ Rays | Rays (57%) | 4.5–4 | 5–10 (home first) |
| ✅ | Nationals @ Rangers | Rangers (52%) | 4.7–4.6 | 5–0 (home first) |
The headline is the paired per-game log-loss difference against a fixed always-pick-home forecast (p=0.534) on the same games, ± one standard error; daily hit rate is noisy and demoted on purpose. Reference points: 0.693 is a coin flip; the model's walk-forward backtest runs 0.680 (research/SP-BACKTEST.md).
Betting-blind Elo model (K=3, +24 home, MOV-weighted, 60% season carryover) · Can Tre Beat Vegas · whosyurgoat.app/vegas/mlb