Points carries the strongest edge (+8.1 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 — and looks the
same as one that does not work.
MarketAll predictionsServed (70+)Share served
Points+8.1 pp n=453+21.0 pp n=25256%
“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. Judged on the engine running today: a superseded scorer’s serving share is not a fact about the current one. The columns stay pooled across versions.
Last 30 days · Other qualifying154–8963.4%n=24317 void · 0 pending · avg score 84 · 22 slates
All qualifying160–9263.5%n=252
Featured6–366.7%n=9
Other qualifying154–8963.4%n=243
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.
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Current scoring engine only — 150 predictions from superseded versions excluded.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=110-1.5 pp base 47%
75–79Small sample1–0100.0%n=10+37.3 pp base 63%
80–84Small sample9–190.0%n=106+31.9 pp base 58%
85–89Small sample1–0100.0%n=11+49.7 pp base 50%
90–94Small sample7–750.0%n=140+4.9 pp base 45%
95–98Small sample3–350.0%n=60-4.5 pp base 54%
99–10032–2655.2%n=582+18.1 pp base 37%
Over vs Under
Over154–8963.4%n=243
Under0–0Not gradedn=0
MarketOverUnder
Points63.4% n=243Not graded n=0
Edge finder
SegmentHit ratevs baseRecord30-day trend
Points63.4% n=243+19.6 pp base 44%154–8963% 30d
Consistency
All time
63.4%
154–89 n=243
By month
MonthRecordHit ratevs base
2026-08154–8963.4% n=243+19.6 pp base 44%
Model versions
VersionActiveRecordHit ratevs base
WNBA Points
wnba-pra-v42026-08-21→2026-08-2958–4357.4% n=101+13.9 pp base 44%
4 earlier versions2026-08-03→2026-08-2196–4667.6% n=142+23.7 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.