Track Record ✦ the last 30 days

56.7% Accuracy

72–55 across 127 games

— By Simulation Type —

Simulation Correct Total Accuracy
Baseline ★ leader 78 127 61.4%
Pitcher-weighted 65 127 51.2%
Platoon-weighted 66 127 52.0%
Pitcher + Platoon 73 127 57.5%
Logistic 65 127 51.2%
Random Forest 60 127 47.2%
Consensus 72 127 56.7%
Baseline is leading individual model by 3.9 points. Consensus edges out 4 of 6 sims.

— Per-Team Accuracy —

★ Top 5 teams
Yankees
2–0 100.0%
D-backs
9–1 90.0%
Phillies
5–1 83.3%
Reds
4–1 80.0%
Cardinals
3–1 75.0%
✗ Bottom 5 teams
Mets
1–4 20.0%
Red Sox
2–7 22.2%
White Sox
1–3 25.0%
Rays
2–5 28.6%
Angels
5–11 31.2%

80-point spread between best and worst — Mets 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% 71 52.4% 50.7% -1.7
55-60% 41 57.2% 63.4% +6.2
60-65% 12 62.0% 83.3% +21.4
65-70% 3 66.1% 0.0% -66.1
70%+ 0
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

55.1%

across 132 picks

Home team picks

65.9%

vs MLB home rate ~54%

Unanimous picks

15%

all sims agreed

— Recent Performance —

Last 30 days

★ Best day

3 of 3

Wednesday, August 19 · 100.0%

✗ Worst day

0 of 4

Monday, July 27 · 0.0%

Jul 23 Aug 7 Aug 21
Date Correct Total Accuracy
Fri, Aug 21 5 10 50.0%
Thu, Aug 20 1 2 50.0%
Wed, Aug 19 3 3 100.0%
Tue, Aug 18 2 6 33.3%
Mon, Aug 17 6 7 85.7%
Sun, Aug 16 0 1 0.0%
Sat, Aug 15 3 4 75.0%
Fri, Aug 14 4 5 80.0%
Thu, Aug 13 0 2 0.0%
Wed, Aug 12 2 4 50.0%
Show all 27 days →