Track Record ✦ the last 30 days

54.1% Accuracy

216–183 across 399 games

— By Simulation Type —

Simulation Correct Total Accuracy
Baseline ★ leader 217 399 54.4%
Pitcher-weighted 211 399 52.9%
Platoon-weighted 195 399 48.9%
Pitcher + Platoon 213 399 53.4%
Logistic 179 399 44.9%
Random Forest 199 399 49.9%
Consensus 216 399 54.1%
Baseline is leading individual model by 1.0 points. Consensus edges out 5 of 6 sims.

— Per-Team Accuracy —

★ Top 5 teams
Giants
19–7 73.1%
Phillies
18–8 69.2%
Rangers
18–9 66.7%
Orioles
17–9 65.4%
Dodgers
17–9 65.4%
✗ Bottom 5 teams
Red Sox
10–17 37.0%
White Sox
11–16 40.7%
Twins
11–15 42.3%
Angels
11–15 42.3%
Reds
12–16 42.9%

36-point spread between best and worst — Red Sox 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% 258 52.2% 52.7% +0.5
55-60% 101 57.0% 55.4% -1.5
60-65% 32 61.6% 65.6% +4.1
65-70% 6 66.4% 33.3% -33.0
70%+ 2 75.5% 50.0% -25.5
Well-calibrated up to 65%, then meaningful overconfidence kicks in.

— Lineup Impact —

Lineup status Games Correct Accuracy
Real lineups 1280 694 54.2%
Fallback lineups 545 319 58.5%
Fallback-lineup predictions are 4.3 points more accurate. 30% of season picks rely on fallback lineups.

— Pick Distribution —

Avg confidence

54.5%

across 414 picks

Home team picks

60.6%

vs MLB home rate ~54%

Unanimous picks

11%

all sims agreed

— Recent Performance —

Last 30 days

★ Best day

12 of 15

Tuesday, August 4 · 80.0%

✗ Worst day

3 of 16

Wednesday, July 29 · 18.8%

Jul 23 Aug 7 Aug 21
Date Correct Total Accuracy
Fri, Aug 21 9 15 60.0%
Thu, Aug 20 6 9 66.7%
Wed, Aug 19 11 15 73.3%
Tue, Aug 18 9 15 60.0%
Mon, Aug 17 8 11 72.7%
Sun, Aug 16 7 15 46.7%
Sat, Aug 15 7 15 46.7%
Fri, Aug 14 9 14 64.3%
Thu, Aug 13 3 9 33.3%
Wed, Aug 12 9 15 60.0%
Show all 30 days →