Are the signals earning trust?

Performance

Daily results β†’
Cohort
Period
Market
All
⚾ Batter
Direction
SP Strikeouts carries the strongest edge (+14.8 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 Strikeouts+14.8 pp n=166+15.8 pp n=15090%
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 30 days Β· All qualifying72–7848.0%n=1505 void Β· 0 pending Β· avg score 86 Β· 22 slates
All qualifying72–7848.0%n=150
Featured9–469.2%n=13
Other qualifying63–7446.0%n=137
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 Strikeouts48%n=150↑ +13 pp56%n=957%n=736%n=1144%n=90%n=650%n=850%n=643%n=14
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, 85–89, 90–94, 95–98 bands remain small.

Current scoring engine only β€” 82 predictions from superseded versions excluded.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 sample2–340.0%n=51-10.0 pp base 50%
85–89Small sample1–516.7%n=60-6.1 pp base 23%
90–94Small sample5–1131.2%n=160-8.6 pp base 40%
95–98Small sample2–625.0%n=80-1.5 pp base 26%
99–10020–1557.1%n=352+24.1 pp base 33%

Over vs Under

Over72–7848.0%n=150
Under0–0Not gradedn=0
MarketOverUnder
SP Strikeouts48.0% n=150Not graded n=0

Edge finder

SegmentHit ratevs baseRecord30-day trend
SP Strikeouts48.0% n=150+15.7 pp base 32%72–7848% 30d

Consistency

Last 7
42.9%
24–32 n=56
Last 30
48.0%
72–78 n=150
Prev 30
Not graded
0–0
Season
48.0%
72–78 n=150
All time
48.0%
72–78 n=150

By month

MonthRecordHit ratevs base
2026-0872–7848.0% n=150+15.7 pp base 32%

Model versions

VersionActiveRecordHit ratevs base
MLB SP Strikeouts
sp-v42026-08-21β†’2026-08-2830–4042.9% n=70+8.5 pp base 34%
3 earlier versions2026-08-03β†’2026-08-2042–3852.5% n=80+22.0 pp base 30%
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.