Track Record ✦ this season

58.9% Accuracy

215–150 across 365 games · season opened March 26

— By Simulation Type —

Simulation Correct Total Accuracy
Baseline 192 365 52.6%
Pitcher-weighted 185 365 50.7%
Platoon-weighted 196 365 53.7%
Pitcher + Platoon 191 365 52.3%
Logistic 186 365 51.0%
Random Forest ★ leader 237 365 64.9%
Consensus 215 365 58.9%
Random Forest is leading individual model by 11.2 points. Consensus edges out 5 of 6 sims.

— Per-Team Accuracy —

★ Top 5 teams
Padres
26–8 76.5%
Astros
15–6 71.4%
Mets
14–6 70.0%
Angels
27–13 67.5%
Reds
10–5 66.7%
✗ Bottom 5 teams
Royals
5–8 38.5%
White Sox
5–8 38.5%
Yankees
8–11 42.1%
Cubs
12–16 42.9%
Braves
12–14 46.2%

38-point spread between best and worst — Royals the hardest to call.

— Confidence Calibration —

Are our confidence numbers honest? Compare what we said to what actually happened.

Confidence band Picks Avg predicted Actual rate Gap
50-55% 187 52.4% 52.9% +0.5
55-60% 104 57.3% 61.5% +4.2
60-65% 51 61.9% 66.7% +4.8
65-70% 8 67.5% 87.5% +20.0
70%+ 14 75.1% 71.4% -3.7
Calibration drifts up to 20.0 points across bands.

— Lineup Impact —

Lineup status Games Correct Accuracy
Real lineups 902 497 55.1%
Fallback lineups 365 215 58.9%
Fallback-lineup predictions are 3.8 points more accurate. 29% of season picks rely on fallback lineups.

— Pick Distribution —

Avg confidence

56.3%

across 367 picks

Home team picks

69.2%

vs MLB home rate ~54%

Unanimous picks

14%

all sims agreed

— Recent Performance —

Last 30 days

★ Best day

3 of 3

Monday, July 6 · 100.0%

✗ Worst day

0 of 2

Wednesday, June 17 · 0.0%

Jun 8 Jun 23 Jul 7
Date Correct Total Accuracy
Tue, Jul 7 1 4 25.0%
Mon, Jul 6 3 3 100.0%
Sun, Jul 5 1 1 100.0%
Sat, Jul 4 5 7 71.4%
Fri, Jul 3 1 6 16.7%
Thu, Jul 2 2 3 66.7%
Wed, Jul 1 2 3 66.7%
Tue, Jun 30 1 4 25.0%
Mon, Jun 29 4 6 66.7%
Sat, Jun 27 2 4 50.0%
Show all 28 days →