Are the signals earning trust?

Performance

Daily results β†’
Cohort
Period
Market
All
⚾ Batter
Direction
Rebounds carries the strongest edge (+18.3 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
Rebounds+18.3 pp n=322+32.1 pp n=17655%
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· Other qualifying110–4770.1%n=1576 void Β· 0 pending Β· avg score 85 Β· 21 slates
All qualifying119–5767.6%n=176
Featured9–1047.4%n=19
Other qualifying110–4770.1%n=157
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
Rebounds70%n=157β†’ -1 pp77%n=13100%n=550%n=670%n=1060%n=586%n=1467%n=1264%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, 75–79, 80–84, 85–89, 90–94, 95–98 bands remain small.

Current scoring engine only β€” 84 predictions from superseded versions excluded.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 sample1–0100.0%n=10+44.9 pp base 55%
75–79Small sample3–350.0%n=60-5.1 pp base 55%
80–84Small sample3–350.0%n=60+12.9 pp base 37%
85–89Small sample4–180.0%n=50+24.9 pp base 55%
90–94Small sample3–175.0%n=40+25.3 pp base 50%
95–98Small sample4–0100.0%n=41+53.6 pp base 46%
99–10037–1374.0%n=502+39.6 pp base 34%

Over vs Under

Over110–4770.1%n=157
Under0–0Not gradedn=0
MarketOverUnder
Rebounds70.1% n=157Not graded n=0

Edge finder

SegmentHit ratevs baseRecord30-day trend
Rebounds70.1% n=157+32.7 pp base 37%110–4770% 30d

Consistency

Last 7
73.8%
48–17 n=65
Last 30
70.1%
110–47 n=157
Prev 30
Not graded
0–0
Season
70.1%
110–47 n=157
All time
70.1%
110–47 n=157

By month

MonthRecordHit ratevs base
2026-08110–4770.1% n=157+32.7 pp base 37%

Model versions

VersionActiveRecordHit ratevs base
WNBA Rebounds
wnba-pra-v42026-08-21β†’2026-08-2855–2172.4% n=76+33.1 pp base 39%
4 earlier versions2026-08-03β†’2026-08-2055–2667.9% n=81+32.3 pp base 36%
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.