⚾ Trueline
PST
Updated 11:59:22 AM PST

Games (15) 2026-05-30 12:00 PM PST

  • DET DET @ CWS CWS 11:10 AM PST ✓ ready In Progress
  • KC KC @ TEX TEX 1:05 PM PST ✓ ready
  • SD SD @ WSH WSH 1:05 PM PST ✓ ready
  • TOR TOR @ BAL BAL 1:05 PM PST ✓ ready
  • MIN MIN @ PIT PIT 1:05 PM PST ✓ ready
  • BOS BOS @ CLE CLE 1:10 PM PST ✓ ready
  • LAA LAA @ TB TB 1:10 PM PST ✓ ready
  • MIA MIA @ NYM NYM 1:10 PM PST ✓ ready
  • MIL MIL @ HOU HOU 1:10 PM PST ✓ ready
  • CHC CHC @ STL STL 4:15 PM PST ⏳ lineups
  • ATL ATL @ CIN CIN 4:15 PM PST ⏳ partial
  • SF SF @ COL COL 6:10 PM PST ⏳ lineups
  • NYY NYY @ ATH ATH 7:05 PM PST ⏳ lineups
  • ARI ARI @ SEA SEA 7:10 PM PST ⏳ lineups
  • PHI PHI @ LAD LAD 7:10 PM PST ⏳ lineups

6 game(s) waiting on lineups. Predictions appear after both teams post — usually 2-3 hours before first pitch. Hit ↻ Rosters in the top bar to refetch.

Predictions (1 picks) 2026-05-30
ⓘ What do these mean?

Every pick falls into one tier based on the model's confidence. Each tier is a strict rule on per-model probabilities; calibrated on 1,800 games.

Badge Rule Hit % n / season Notes
ELITE all 4 models agree > 62% 82.9% 35 Rare (~2% of slate) · safest tier
STRONG any 2 of 3 primary models > 60% 62.0% 234 Workhorse · most volume
VALUE all 3 primary models > 55% 64.7% 153 Best ROI tier · +odds friendly · parlay-grade
TOTALS-LOCK LR ≥ 0.62 and sim ≥ 0.62, same side 68.2% 107 D2 consensus · highest confidence band
TOTALS-STRONG LR ≥ 0.60 and sim ≥ 0.55, same side 65.7% 277 D2 consensus · workhorse totals band
TOTALS-VALUE LR ≥ 0.58 and sim ≥ 0.52, same side 58.4% 197 D2 consensus · wider band, parlay-grade
TOTALS-LR-SOLO LR ≥ 0.66, sim disagrees — 0 Forward-compatible · 0 picks across n=3,638 games to date
PASS no tier rule matches ~50% — Collapsed by default · add manually if your read differs

How to read tier colors: green = LOCK band (~9–10/10 confidence), amber = STRONG, blue = LEAN/VALUE, grey = PASS.

Lineup gate: predictions only appear once both starting lineups are posted. Games waiting on lineups show ⏳ lineups in the left column — usually 2–3 hours before first pitch. For future-dated slates, predictions show with a ⏳ tentative roster badge — they use probable pitchers + team strength only (no lineup data yet).

Models behind the picks: analytic generative (Negative-Binomial run distribution), simulation Monte-Carlo (2,000 sims/game), LR classifier (elastic-net), and XGBoost (gradient-boosted trees). ELITE requires all four; STRONG / VALUE require the three primary voters (XGB optional). On totals, the user-facing tier is the new D2 LR + sim consensus rule — both voters must agree on side at the threshold; LR is the peaked-accuracy anchor and sim is the agreement check.

Sim is now multi-line (D1): sim emits a probability at every standard market line 7.5 → 11.5 in 0.5 increments — matching LR's classifier coverage. The 8.5 / 8.0 / 11.0 / 11.5 calibrators are persisted (isotonic, refuse-if-worse gate); 7.5 / 9.0 / 9.5 / 10.0 / 10.5 currently use sim's raw probability because the calibrator didn't improve held-out log-loss.

Why fewer non-8.5 ensemble totals (D3): at non-8.5 lines, only sim emits — there's nothing to average against, so the "ensemble" is just sim's raw probability. To prevent single-voter overconfidence at the tails, the ensemble blender requires ≥ 2 voters per line; below that it emits nothing. Net effect: ensemble Total Brier 0.2454 → 0.2451 with the gate on, and the Δ +0.13 / +0.22 overconfidence at P ≥ 0.60 went to within ±0.04.

Headline lift from Wave 1 + D1 + D2 + D3 (n=1,800): totals consensus tier hit-rate 62.5% → 63.7% · ROI at −110 +19.4% → +21.6% · ensemble Brier 0.2340 → 0.2316. ML side: essentially unchanged (only C8 batter recency feeds into ML and the n=1,800 delta is +0.0001 — noise).

Full model card with Brier progression, totals verification, and EV-backtest tables: /model-card

Strong (1)

  • ML CWS DET@CWS
    STRONG 62.0% | -196

All Bets by Probability

Every standard side across the slate — ML home/away, O/U at the market line, run line ±1.5 — grouped by the model's win probability (each row's model P).

70%+ (1)

  • RUN LINE CWS +1.5 DET@CWS
    71% | -301

65–70% (1)

  • RUN LINE MIA +1.5 MIA@NYM
    65% | -234

60–65% (3)

  • RUN LINE MIN +1.5 MIN@PIT
    64% | -220
  • RUN LINE WSH +1.5 SD@WSH
    62% | -202
  • RUN LINE KC +1.5 KC@TEX
    61% | -197

55–60% (7)

  • RUN LINE LAA +1.5 LAA@TB
    59% | -182
  • RUN LINE BAL +1.5 TOR@BAL
    59% | -179
  • ML TB LAA@TB
    57% | -165
  • TOTAL Under 8.5 MIN@PIT
    57% | -164
  • ML MIL MIL@HOU
    57% | —
  • ML NYM MIA@NYM
    55% | -155
  • TOTAL Under 8 KC@TEX
    55% | -153

50–55% (12)

  • ML SD SD@WSH
    55% | -150
  • ML CLE BOS@CLE
    54% | -148
  • ML TOR TOR@BAL
    54% | -146
  • TOTAL Over 7.5 SD@WSH
    54% | -144
  • TOTAL Over 7.5 TOR@BAL
    53% | -141
  • ML PIT MIN@PIT
    52% | -137
  • ML TEX KC@TEX
    51% | -129
  • TOTAL Under 7.5 DET@CWS
    50% | -127
  • TOTAL Over 7 LAA@TB
    50% | -125
  • TOTAL Under 7 LAA@TB
    50% | -125
  • TOTAL Over 7 MIA@NYM
    50% | -125
  • TOTAL Under 7 MIA@NYM
    50% | -125

45–50% (8)

  • TOTAL Over 7.5 DET@CWS
    50% | -123
  • ML KC KC@TEX
    49% | -121
  • ML MIN MIN@PIT
    48% | -114
  • TOTAL Under 7.5 TOR@BAL
    47% | -111
  • TOTAL Under 7.5 SD@WSH
    46% | -109
  • ML BAL TOR@BAL
    46% | -107
  • ML BOS BOS@CLE
    46% | -106
  • ML WSH SD@WSH
    45% | -104

<45% (17)

  • TOTAL Over 8 KC@TEX
    45% | -102
  • ML MIA MIA@NYM
    45% | -101
  • ML HOU MIL@HOU
    43% | —
  • TOTAL Over 8.5 MIN@PIT
    43% | +105
  • ML LAA LAA@TB
    43% | +105
  • RUN LINE TOR -1.5 TOR@BAL
    41% | +115
  • RUN LINE TB -1.5 LAA@TB
    41% | +117
  • ML DET DET@CWS
    39% | +126
  • RUN LINE TEX -1.5 KC@TEX
    39% | +126
  • RUN LINE MIL -1.5 MIL@HOU
    39% | —
  • RUN LINE SD -1.5 SD@WSH
    38% | +129
  • RUN LINE BOS -1.5 BOS@CLE
    37% | —
  • RUN LINE PIT -1.5 MIN@PIT
    36% | +141
  • RUN LINE CLE -1.5 BOS@CLE
    36% | +144
  • RUN LINE NYM -1.5 MIA@NYM
    35% | +150
  • RUN LINE DET -1.5 DET@CWS
    29% | +193
  • RUN LINE HOU -1.5 MIL@HOU
    28% | —

Use these to build slips even when your read differs from the model — EV/Kelly still uses the model's actual probability for each leg.

Strategy

⚙️ Settings

$
$
%

Changes persist; recompute is automatic.

🔒 Recommended Parlay AUTO

No qualifying legs.

Risk

🧾 Slip 1 0/8 legs

Click ＋ on a prediction to fill this parlay.

Stake