Track Record ✦ this season

56.8% Accuracy

351–267 across 618 games · season opened March 26

— By Simulation Type —

Simulation Correct Total Accuracy
Baseline 348 618 56.3%
Pitcher-weighted 322 618 52.1%
Platoon-weighted 327 618 52.9%
Pitcher + Platoon 325 618 52.6%
Logistic 313 618 50.6%
Random Forest ★ leader 354 618 57.3%
Consensus 351 618 56.8%
Random Forest is leading individual model by 1.0 points. Consensus edges out 5 of 6 sims.

— Per-Team Accuracy —

★ Top 5 teams
Padres
43–17 71.7%
Tigers
20–9 69.0%
Dodgers
48–25 65.8%
Rockies
38–21 64.4%
Pirates
23–14 62.2%
✗ Bottom 5 teams
White Sox
8–15 34.8%
Yankees
12–21 36.4%
Cubs
20–24 45.5%
Giants
27–30 47.4%
Red Sox
16–16 50.0%

37-point spread between best and worst — White 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% 332 52.4% 52.4% +0.0
55-60% 188 57.3% 58.5% +1.2
60-65% 69 61.9% 69.6% +7.7
65-70% 12 67.2% 66.7% -0.6
70%+ 15 74.8% 66.7% -8.1
Well-calibrated up to 70%+%, then meaningful overconfidence kicks in.

— Lineup Impact —

Lineup status Games Correct Accuracy
Real lineups 1724 933 54.1%
Fallback lineups 618 351 56.8%
Fallback-lineup predictions are 2.7 points more accurate. 26% of season picks rely on fallback lineups.

— Pick Distribution —

Avg confidence

55.8%

across 619 picks

Home team picks

67.2%

vs MLB home rate ~54%

Unanimous picks

14%

all sims agreed

— Recent Performance —

Last 30 days

★ Best day

2 of 2

Saturday, September 26 · 100.0%

✗ Worst day

0 of 2

Friday, September 11 · 0.0%

Sep 11 Sep 26 Oct 10
Date Correct Total Accuracy
Thu, Oct 8 0 1 0.0%
Wed, Oct 7 1 4 25.0%
Mon, Oct 5 0 1 0.0%
Sun, Sep 27 0 1 0.0%
Sat, Sep 26 2 2 100.0%
Fri, Sep 25 1 3 33.3%
Thu, Sep 24 0 1 0.0%
Wed, Sep 23 1 1 100.0%
Tue, Sep 22 1 1 100.0%
Mon, Sep 21 0 1 0.0%
Show all 16 days →