Are the signals earning trust?

Performance

Daily results β†’
Cohort
Period
Market
All
⚾ Batter
Direction
Rebounds carries the strongest edge (+31.1 pts over base). Down 10.9 points vs previous 7 days.

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+31.1 pp n=89+33.1 pp n=8191%
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 7 days Β· All qualifying56–2569.1%n=815 void Β· 0 pending Β· avg score 96 Β· 7 slates
All qualifying56–2569.1%n=81
Featured8–850.0%n=16
Other qualifying48–1773.8%n=65
69.1% hit rate, down 10.9 percentage points vs previous 7 days
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.

MarketPeriodAug28Aug27Aug26Aug25Aug24Aug23Aug22
Rebounds69%n=81β†’ -2 pp75%n=1675%n=850%n=862%n=1375%n=875%n=1667%n=12
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.

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 sample3–260.0%n=50+22.2 pp base 38%
85–89Small sample3–175.0%n=40+19.9 pp base 55%
90–94Small sample2–166.7%n=30+11.6 pp base 55%
95–98Small sample4–0100.0%n=41+53.6 pp base 46%
99–10040–1869.0%n=584+38.4 pp base 31%

Over vs Under

Over56–2569.1%n=81
Under0–0Not gradedn=0
MarketOverUnder
Rebounds69.1% n=81Not graded n=0

Edge finder

SegmentHit ratevs baseRecord30-day trend
Rebounds69.1% n=81+33.2 pp base 36%56–2569% 30d

Consistency

Last 7
69.1%
56–25 n=81
Last 30
68.4%
119–55 n=174
Prev 30
0.0%
0–2 n=2
Season
67.6%
119–57 n=176
All time
67.6%
119–57 n=176

By month

MonthRecordHit ratevs base
2026-070–20.0% n=2-30.7 pp base 31%
2026-08119–5568.4% n=174+32.8 pp base 36%

Model versions

VersionActiveRecordHit ratevs base
WNBA Rebounds
wnba-pra-v42026-08-21β†’2026-08-2863–2968.5% n=92+32.7 pp base 36%
4 earlier versions2026-07-15β†’2026-08-2056–2866.7% n=84+31.5 pp base 35%
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.