Are the signals earning trust?

Performance

SP Strikeouts carries the strongest edge (+7.9 pts over base). Over is currently the stronger side (+35.8 pts vs -21.6 pts for Under).

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 — and looks the same as one that does not work.

MarketAll predictionsServed (70+)Share served

SP Strikeouts+7.9 pp n=530+11.0 pp n=40476%

“Starved” means the market beats its base rate by 5+ points across everything it predicted, yet under a tenth of those ever clear the floor — the scale cannot reach, so the edge is never offered.

Last 90 days · Featured10–662.5%n=161 void · 0 pending · avg score 99 · 5 slates

All qualifying234–17057.9%n=404

Featured10–662.5%n=16

Other qualifying224–16457.7%n=388

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.

MarketPeriodAug26Aug22Aug21Aug11Aug10

SP Strikeouts62%n=16building sample100%n=450%n=450%n=6100%n=10%n=1

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 99–100 band remains small.

Current scoring engine only — 2 predictions from superseded versions excluded.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

99–100Small sample9–564.3%n=141+28.0 pp base 36%

Over vs Under

Over9–469.2%n=13

Under1–233.3%n=3

Difference: +35.9 pp · Over stronger

MarketOverUnder

SP Strikeouts69.2% n=1333.3% n=3

Edge finder

SegmentHit ratevs baseRecord30-day trend

Below minimum sample

SP StrikeoutsSmall62.5% n=16+25.3 pp base 37%10–662% 30d

Consistency

Last 7

75.0%

6–2 n=8

Last 30

62.5%

10–6 n=16

Prev 30

Not graded

0–0

Season

62.5%

10–6 n=16

All time

62.5%

10–6 n=16

By month

MonthRecordHit ratevs base

2026-0810–662.5% n=16+25.3 pp base 37%

Model versions

VersionActiveRecordHit ratevs base

MLB SP Strikeouts

sp-v42026-08-21→2026-08-269–564.3% n=14+28.0 pp base 36%

2 earlier versions2026-08-10→2026-08-111–150.0% n=2+6.2 pp base 44%

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.