SOG Model — Performance
Today's board · Pick historyAll picks
1558-1512
+13.40u · ROI +0.4%
Best bets
509-465
+54.26u · ROI +5.6%
Leans
1049-1047
-40.85u · ROI -1.9%
Avg CLV
—
n/a — priced at close
Log loss · model / book
0.6818 / 0.6829
41,351 lines · lower is better
Cumulative units flat 1u per pick at Hard Rock's price
BestLean
By month
| Month | Record | Win % | Units | ROI | CLV |
|---|---|---|---|---|---|
| 2024-10 | 51-53 | 49.0% | +0.16 | +0.2% | — |
| 2024-11 | 32-30 | 51.6% | +4.04 | +6.5% | — |
| 2024-12 | 260-263 | 49.7% | -15.69 | -3.0% | — |
| 2025-01 | 217-188 | 53.6% | +17.99 | +4.4% | — |
| 2025-02 | 58-57 | 50.4% | -1.38 | -1.2% | — |
| 2025-03 | 91-102 | 47.2% | -18.35 | -9.5% | — |
| 2025-04 | 64-64 | 50.0% | +2.14 | +1.7% | — |
| 2025-05 | 36-20 | 64.3% | +16.00 | +28.6% | — |
| 2025-06 | 11-15 | 42.3% | -4.63 | -17.8% | — |
| 2025-10 | 156-150 | 51.0% | +6.44 | +2.1% | — |
| 2025-11 | 55-50 | 52.4% | +6.89 | +6.6% | — |
| 2025-12 | 57-51 | 52.8% | +11.89 | +11.0% | — |
| 2026-01 | 56-64 | 46.7% | -3.79 | -3.2% | — |
| 2026-02 | 7-13 | 35.0% | -6.25 | -31.3% | — |
| 2026-03 | 51-69 | 42.5% | -14.65 | -12.2% | — |
| 2026-04 | 74-63 | 54.0% | +9.38 | +6.8% | — |
| 2026-05 | 37-30 | 55.2% | +10.28 | +15.3% | — |
| 2026-06 | 9-4 | 69.2% | +5.48 | +42.2% | — |
| 2026-09 | 10-7 | 58.8% | +2.53 | +14.9% | — |
| 2026-10 | 226-219 | 50.8% | -15.07 | -3.4% | — |
By line
| Line | Record | Win % | Units | ROI | CLV |
|---|---|---|---|---|---|
| 0.5 | 1-1 | 50.0% | -0.36 | -17.8% | — |
| 1.5 | 540-618 | 46.6% | -27.88 | -2.4% | — |
| 2.5 | 775-689 | 52.9% | +45.90 | +3.1% | — |
| 3.5 | 232-200 | 53.7% | -8.68 | -2.0% | — |
| 4.5 | 10-4 | 71.4% | +4.42 | +31.5% | — |
By side
| Side | Record | Win % | Units | ROI | CLV |
|---|---|---|---|---|---|
| OVER | 191-192 | 49.9% | +2.33 | +0.6% | — |
| UNDER | 1367-1320 | 50.9% | +11.07 | +0.4% | — |
By tier
| Tier | Record | Win % | Units | ROI | CLV |
|---|---|---|---|---|---|
| best | 509-465 | 52.3% | +54.26 | +5.6% | — |
| lean | 1049-1047 | 50.0% | -40.85 | -1.9% | — |
By position
| Position | Record | Win % | Units | ROI | CLV |
|---|---|---|---|---|---|
| D | 362-336 | 51.9% | +11.44 | +1.6% | — |
| F | 1196-1176 | 50.4% | +1.96 | +0.1% | — |
Calibration model P(over) vs how often it hit
| Model P | Lines | Predicted | Hit | Book |
|---|---|---|---|---|
| 20–30% | 10 | 27.9% | 40.0% | 38.6% |
| 30–40% | 4,935 | 37.6% | 36.7% | 40.2% |
| 40–50% | 14,801 | 45.2% | 44.5% | 46.3% |
| 50–60% | 18,081 | 54.9% | 54.2% | 55.4% |
| 60–70% | 3,525 | 61.7% | 61.6% | 60.7% |
| 70–80% | 1 | 70.5% | 100.0% | 66.0% |
Walk-forward backtest report
2024-10-04 → 2026-10-18 · 41,351 Hard Rock closing lines · run 2026-10-19
Verdict: SHADOW PASS requires beating every baseline, a log-loss edge over Hard Rock whose 95% interval excludes zero, and best-bet ROI whose 95% interval is above zero. Otherwise the model stays in shadow mode.
| Method | Log loss | Brier |
|---|---|---|
| Production probability (sim × market blend) | 0.68181 | 0.24438 |
| Simulation only | 0.68388 | 0.24535 |
| Model without game script | 0.68403 | 0.24542 |
| Model without market inputs | 0.68386 | 0.24534 |
| Season average (Poisson) | 0.69597 | 0.25075 |
| Last 10 (Poisson) | 0.71375 | 0.25855 |
| LightGBM challenger | 0.68454 | 0.24568 |
| Hard Rock (de-vigged) | 0.68288 | 0.24490 |
- Production (blend) − market log loss
- -0.00106 95% CI [-0.0015, -0.0006] (negative = better than Hard Rock's close)
- Simulation-only − market log loss
- +0.00100 95% CI [-0.0001, +0.0022] (negative = model better)
- Best-bet ROI
- +5.6% n=974, 95% CI [-0.6, +11.5]
- Lean ROI
- -2.0% n=2096, 95% CI [-6.4, +2.4]
- Mean SOG · predicted / actual
- 2.217 / 2.237
- Leftover dispersion
- cv² 0.0174 (param 0.0097)
- Zone-start coefficient
- +0.091 ≈0 means zone starts add nothing
Blending the simulation into the market
Log loss when the probability is a logit blend of the simulation (weight w) and Hard Rock (in-sample over the whole backtest, for reference). Production uses a walk-forward weight fitted only on earlier months (by month: 2024-10 0.3, 2024-11 0.3, 2024-12 0.55, 2025-01 0.55, 2025-02 0.55, 2025-03 0.55, 2025-04 0.45, 2025-05 0.5, 2025-06 0.5, 2025-10 0.5, 2025-11 0.45, 2025-12 0.45, 2026-01 0.45, 2026-02 0.4, 2026-03 0.4, 2026-04 0.4, 2026-05 0.4, 2026-06 0.45, 2026-09 0.45, 2026-10 0.45).
| w=0.0 | w=0.1 | w=0.2 | w=0.3 | w=0.5 | w=0.7 | w=1.0 |
|---|---|---|---|---|---|---|
| 0.68288 | 0.68239 | 0.68203 | 0.68180 | 0.68175 | 0.68222 | 0.68388 |
By line
| Line | Lines | Over rate | Blend LL | Sim LL | Book LL | LightGBM LL | Season LL |
|---|---|---|---|---|---|---|---|
| 0.5 | 33 | 63.6% | 0.6448 | 0.6502 | 0.6463 | 0.6538 | 0.6818 |
| 1.5 | 21,326 | 53.7% | 0.6847 | 0.6863 | 0.6853 | 0.6869 | 0.6985 |
| 2.5 | 16,873 | 45.0% | 0.6794 | 0.6819 | 0.6808 | 0.6821 | 0.6931 |
| 3.5 | 2,978 | 42.2% | 0.6758 | 0.6790 | 0.6787 | 0.6821 | 0.6941 |
| 4.5 | 141 | 36.2% | 0.6660 | 0.6631 | 0.6724 | 0.6748 | 0.6975 |
Pre-registered pricing hypotheses
| Hypothesis | Lines | Over hit | Book P(over) | Gap (95% CI) | Blind over ROI | Blind under ROI |
|---|---|---|---|---|---|---|
| H1 · 3.5+ lines (star overs) | 3,119 | 42.0% | 46.1% | -4.1 [-5.7, -2.4] | -15.0% [-18.4, -11.6] | +0.5% [-2.4, +3.3] |
| H3 · 1.5 lines | 21,326 | 53.7% | 54.3% | -0.7 [-1.4, -0.1] | -7.7% [-9.0, -6.6] | -5.1% [-6.4, -3.7] |
| H2 · role change (last game's PP/EV role differs from his prior 10) | Lines | Sim − market LL (95% CI) | Picks | Pick ROI (95% CI) |
|---|---|---|---|---|
| After a role change | 6,688 | +0.0030 [-0.0001, +0.0057] | 621 | -1.1% [-9.1, +6.6] |
| No role change | 34,663 | +0.0006 [-0.0006, +0.0017] | 2449 | +0.8% [-3.3, +4.9] |