Are the signals earning trust?

Performance

Daily results β†’
Cohort
Period
Market
All
⚾ Batter
Direction
SP Strikeouts carries the strongest edge (+5.0 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+5.0 pp n=381+8.7 pp n=26870%
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 qualifying172–9664.2%n=2683 void Β· 0 pending Β· avg score 82 Β· 23 slates
All qualifying172–9664.2%n=268
Featured1–233.3%n=3
Other qualifying171–9464.5%n=265
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.

MarketPeriodAug29Aug28Aug27Aug26Aug25Aug24Aug23Aug22
SP Strikeouts64%n=268↑ +14 pp71%n=1490%n=1060%n=562%n=1362%n=1362%n=869%n=1344%n=9
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 75–79, 85–89, 95–98, 99–100 bands remain small.

Current scoring engine only β€” 176 predictions from superseded versions excluded.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
70–7426–1170.3%n=371+19.8 pp base 50%
75–79Small sample11–473.3%n=150+10.4 pp base 63%
85–89Small sample0–10.0%n=10-50.1 pp base 50%
95–98Small sample19–1065.5%n=291+10.5 pp base 55%
99–100Small sample8–372.7%n=110+22.7 pp base 50%

Over vs Under

Over0–0Not gradedn=0
Under172–9664.2%n=268
MarketOverUnder
SP StrikeoutsNot graded n=064.2% n=268

Edge finder

SegmentHit ratevs baseRecord30-day trend
SP Strikeouts64.2% n=268+8.7 pp base 56%172–9664% 30d

Consistency

Last 7
68.4%
52–24 n=76
Last 30
64.2%
172–96 n=268
Prev 30
Not graded
0–0
Season
64.2%
172–96 n=268
All time
64.2%
172–96 n=268

By month

MonthRecordHit ratevs base
2026-08172–9664.2% n=268+8.7 pp base 56%

Model versions

VersionActiveRecordHit ratevs base
MLB SP Strikeouts
sp-v42026-08-21β†’2026-08-2964–2968.8% n=93+15.0 pp base 54%
3 earlier versions2026-08-03β†’2026-08-20108–6761.7% n=175+5.3 pp base 56%
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.