Are the signals earning trust?

Performance

Daily results β†’
Cohort
Period
Market
All
⚾ Batter
Direction
Points carries the strongest edge (+8.3 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
Points+8.3 pp n=444+21.9 pp n=24555%
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 30 days Β· All qualifying158–8764.5%n=24515 void Β· 0 pending Β· avg score 84 Β· 21 slates
All qualifying158–8764.5%n=245
Featured6–366.7%n=9
Other qualifying152–8464.4%n=236
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
Points64%n=245β†’ +0 pp74%n=1950%n=1060%n=1064%n=1155%n=1171%n=1462%n=1340%n=15
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Current scoring engine only β€” 150 predictions from superseded versions excluded.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 sample5–645.5%n=110-1.7 pp base 47%
75–79Small sample1–0100.0%n=10+37.3 pp base 63%
80–84Small sample8–188.9%n=94+29.9 pp base 59%
85–89Small sample1–0100.0%n=11+49.5 pp base 50%
90–94Small sample7–558.3%n=120+12.0 pp base 46%
95–98Small sample2–340.0%n=50-12.9 pp base 53%
99–10038–2659.4%n=642+24.4 pp base 35%

Over vs Under

Over158–8764.5%n=245
Under0–0Not gradedn=0
MarketOverUnder
Points64.5% n=245Not graded n=0

Edge finder

SegmentHit ratevs baseRecord30-day trend
Points64.5% n=245+21.5 pp base 43%158–8764% 30d

Consistency

Last 7
63.6%
56–32 n=88
Last 30
64.5%
158–87 n=245
Prev 30
100.0%
5–0 n=5
Season
65.2%
163–87 n=250
All time
65.2%
163–87 n=250

By month

MonthRecordHit ratevs base
2026-075–0100.0% n=5+55.8 pp base 44%
2026-08158–8764.5% n=245+21.5 pp base 43%

Model versions

VersionActiveRecordHit ratevs base
WNBA Points
wnba-pra-v42026-08-21β†’2026-08-2862–4160.2% n=103+18.6 pp base 42%
4 earlier versions2026-07-15β†’2026-08-21101–4668.7% n=147+24.7 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.