Track Record ✦ the last 30 days

50.3% Accuracy

151–149 across 300 games

— By Simulation Type —

Simulation Correct Total Accuracy
Baseline 134 300 44.7%
Pitcher-weighted 141 300 47.0%
Platoon-weighted 148 300 49.3%
Pitcher + Platoon 131 300 43.7%
Logistic 153 300 51.0%
Random Forest ★ leader 171 300 57.0%
Consensus 151 300 50.3%
Random Forest is leading individual model by 6.0 points. Consensus edges out 4 of 6 sims.

— Per-Team Accuracy —

★ Top 5 teams
Phillies
15–7 68.2%
Giants
13–7 65.0%
Rangers
11–6 64.7%
Reds
14–8 63.6%
Athletics
12–7 63.2%
✗ Bottom 5 teams
Twins
5–15 25.0%
Rays
6–14 30.0%
Blue Jays
7–14 33.3%
Royals
7–12 36.8%
Cubs
8–13 38.1%

43-point spread between best and worst — Twins 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% 152 52.5% 50.0% -2.5
55-60% 89 57.3% 51.7% -5.6
60-65% 35 62.8% 42.9% -19.9
65-70% 13 67.4% 38.5% -29.0
70%+ 11 73.0% 81.8% +8.9
Overconfidence shows up most in the 55-60% band.

— Lineup Impact —

Lineup status Games Correct Accuracy
Real lineups 456 264 57.9%
Fallback lineups 212 132 62.3%
Fallback-lineup predictions are 4.4 points more accurate. 32% of season picks rely on fallback lineups.

— Pick Distribution —

Avg confidence

56.5%

across 310 picks

Home team picks

50.3%

vs MLB home rate ~54%

Unanimous picks

18%

all sims agreed

— Recent Performance —

Last 30 days

★ Best day

6 of 7

Thursday, May 21 · 85.7%

✗ Worst day

0 of 1

Friday, May 22 · 0.0%

Apr 24 May 9 May 23
Date Correct Total Accuracy
Sat, May 23 2 9 22.2%
Fri, May 22 0 1 0.0%
Thu, May 21 6 7 85.7%
Wed, May 20 7 15 46.7%
Mon, May 18 7 14 50.0%
Sun, May 17 11 15 73.3%
Sat, May 16 4 15 26.7%
Fri, May 15 10 15 66.7%
Thu, May 14 6 11 54.5%
Wed, May 13 5 15 33.3%
Show all 26 days →