Are the signals earning trust?

Performance

Daily results β†’
Cohort
Period
Market
All
⚾ Batter
Direction
SP Hits Allowed carries the strongest edge (-4.4 pts over base).

What's working

Every market's measured edge against how much of it we actually serve, ranked by lift. The tables further down read served predictions only, so a market that is good but never clears the floor is invisible there β€” and looks the same as one that does not work.

MarketAll predictionsServed (70+)Share served
SP Hits Allowed-4.4 pp n=444-2.7 pp n=24856%
β€œStarved” means the market beats its base rate by 5+ points across everything it predicted, yet under a tenth of those ever clear the floor β€” the scale cannot reach, so the edge is never offered.
Last 90 days Β· All qualifying130–11852.4%n=2483 void Β· 0 pending Β· avg score 79 Β· 22 slates
All qualifying130–11852.4%n=248
Featured1–233.3%n=3
Other qualifying129–11652.7%n=245
Deeper diagnostics

Market pulse

Recent slate hit rates compared with each market’s own average. The right edge shows the selected period and the latest three slates versus the prior three.

MarketPeriodAug28Aug27Aug26Aug25Aug24Aug23Aug22Aug21
SP Hits Allowed52%n=248↑ +18 pp69%n=1362%n=838%n=825%n=860%n=544%n=962%n=1327%n=11
Above own averageNear own averageBelow own averageFaded cells have fewer than 5 decisions

Does a higher score perform better?

Not enough graded props yet to judge whether higher scores perform better. The 70–74, 80–84, 95–98, 99–100 bands remain small.

Current scoring engine only β€” 174 predictions from superseded versions excluded. Pooling engines once made the top band look anti-predictive when it was not; per-version records are in the model table below.

Score bandRecordHit rateSampleVoidsvs base
70–74Small sample4–0100.0%n=40+53.4 pp base 47%
75–7918–2541.9%n=432-9.6 pp base 51%
80–84Small sample0–20.0%n=20-46.6 pp base 47%
95–98Small sample0–10.0%n=10-63.3 pp base 63%
99–100Small sample15–1060.0%n=250+8.1 pp base 52%

Over vs Under

Over0–0Not gradedn=0
Under130–11852.4%n=248
MarketOverUnder
SP Hits AllowedNot graded n=052.4% n=248

Edge finder

SegmentHit ratevs baseRecord30-day trend
SP Hits Allowed52.4% n=248-2.6 pp base 55%130–11852% 30d

Consistency

Last 7
53.1%
34–30 n=64
Last 30
52.4%
130–118 n=248
Prev 30
Not graded
0–0
Season
52.4%
130–118 n=248
All time
52.4%
130–118 n=248

By month

MonthRecordHit ratevs base
2026-08130–11852.4% n=248-2.6 pp base 55%

Model versions

VersionActiveRecordHit ratevs base
MLB SP Hits Allowed
sp-v42026-08-21β†’2026-08-2837–3849.3% n=75-2.0 pp base 51%
3 earlier versions2026-08-03β†’2026-08-2093–8053.8% n=173-2.9 pp base 57%
All qualifying includes every published prediction scoring 70+. Featured is the main-page eight. Observed hit rates are not probabilities; prediction counts are correlated within the displayed slate count.