Are the signals earning trust?

Performance

Assists carries the strongest edge (+23.2 pts over base). Batter Hits is the volume leader (5,938 graded, -3.6 pts). Over is currently the stronger side (+17.7 pts vs -23.0 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

Assists+23.2 pp n=269+33.0 pp n=15959%

Rebounds+18.3 pp n=322+32.1 pp n=17655%

Batter Ks+16.6 pp n=138+28.2 pp n=1410%

Points+8.8 pp n=449+22.6 pp n=25056%

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

SP Hits Allowed-3.1 pp n=530-0.6 pp n=32161%

Batter Hits-3.6 pp n=5,938+2.7 pp n=1,48525%

“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 · Featured128–6965.0%n=19720 void · 0 pending · avg score 98 · 27 slates

All qualifying1730–107961.6%n=2809

Featured128–6965.0%n=197

Other qualifying1602–101061.3%n=2612

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

Batter Hits63%n=122building sample————————

SP Strikeouts62%n=16building sample——100%n=4———50%n=450%n=6

SP Hits Allowed62%n=8building sample——100%n=1———67%n=350%n=2

Points79%n=14building sample100%n=2100%n=1——0%n=3100%n=3——

Rebounds47%n=19building sample67%n=333%n=350%n=233%n=3100%n=30%n=2——

Assists89%n=18building sample100%n=375%n=4100%n=1100%n=450%n=2100%n=3——

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.

Current scoring engine only — 152 predictions from superseded versions excluded.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

99–10042–2067.7%n=623+42.7 pp base 25%

Over vs Under

Over126–6566.0%n=191

Under2–433.3%n=6

Difference: +32.6 pp · Over stronger

MarketOverUnder

Batter Hits63.1% n=122Not graded n=0

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

SP Hits Allowed80.0% n=533.3% n=3

Points78.6% n=14Not graded n=0

Rebounds47.4% n=19Not graded n=0

Assists88.9% n=18Not graded n=0

Edge finder

SegmentHit ratevs baseRecord30-day trend

Batter Hits63.1% n=122+2.5 pp base 61%77–4563% 30d

Below minimum sample

ReboundsSmall47.4% n=19+26.1 pp base 21%9–1047% 30d

AssistsSmall88.9% n=18+65.7 pp base 23%16–289% 30d

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

PointsSmall78.6% n=14+49.4 pp base 29%11–379% 30d

SP Hits AllowedSmall62.5% n=8+20.0 pp base 43%5–362% 30d

Consistency

Last 7

70.4%

38–16 n=54

Last 30

64.3%

110–61 n=171

Prev 30

69.2%

18–8 n=26

Season

65.0%

128–69 n=197

All time

65.0%

128–69 n=197

By month

MonthRecordHit ratevs base

2026-0718–869.2% n=26+16.1 pp base 53%

2026-08110–6164.3% n=171+16.6 pp base 48%

Model versions

VersionActiveRecordHit ratevs base

MLB Batter Hits

4 earlier versions2026-07-05→2026-08-2077–4563.1% n=122+2.5 pp base 61%

WNBA Rebounds

wnba-pra-v42026-08-23→2026-08-288–850.0% n=16+29.7 pp base 20%

2 earlier versions2026-07-15→2026-08-201–233.3% n=3+7.8 pp base 26%

WNBA Assists

wnba-pra-v42026-08-23→2026-08-2815–288.2% n=17+69.8 pp base 18%

1 earlier version2026-07-15→2026-07-161–0100.0% n=1+56.6 pp base 43%

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%

WNBA Points

wnba-pra-v42026-08-23→2026-08-286–366.7% n=9+45.9 pp base 21%

1 earlier version2026-07-15→2026-07-155–0100.0% n=5+55.8 pp base 44%

MLB SP Hits Allowed

sp-v42026-08-21→2026-08-264–266.7% n=6+31.1 pp base 36%

1 earlier version2026-08-10→2026-08-101–150.0% n=2-13.3 pp base 63%

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.