Are the signals earning trust?

Performance

Batter Hits carries the strongest edge (-3.8 pts over base). Up 0.4 points vs previous 30 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 — and looks the same as one that does not work.

MarketAll predictionsServed (70+)Share served

Batter Hits-3.8 pp n=5,944+3.1 pp n=1,36223%

“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 Judged on the engine running today: a superseded scorer’s serving share is not a fact about the current one.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 qualifying803–45563.8%n=1258136 void · 0 pending · avg score 78 · 23 slates

All qualifying868–49463.7%n=1362

Featured65–3962.5%n=104

Other qualifying803–45563.8%n=1258

63.8% hit rate, up 0.4 percentage points vs previous 30 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.

MarketPeriodAug29Aug28Aug27Aug26Aug25Aug24Aug23Aug22

Batter Hits64%n=1258↑ +12 pp74%n=6268%n=6663%n=1954%n=5051%n=5975%n=3676%n=4663%n=52

Above own averageNear own averageBelow own averageFaded cells have fewer than 5 decisions

Does a higher score perform better?

Score bands have produced broadly similar hit rates so far. The 85–89 band remains small.

Current scoring engine only — 927 predictions from superseded versions excluded.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

70–74177–8667.3%n=26316+6.7 pp base 61%

75–7978–5459.1%n=1328-1.5 pp base 61%

80–8428–1270.0%n=401+9.4 pp base 61%

85–89Small sample5–271.4%n=70+10.8 pp base 61%

Over vs Under

Over803–45563.8%n=1258

Under0–0Not gradedn=0

MarketOverUnder

Batter Hits63.8% n=1258Not graded n=0

Edge finder

SegmentHit ratevs baseRecord30-day trend

Batter Hits63.8% n=1258+3.2 pp base 61%803–45564% 30d

Consistency

Last 7

65.7%

222–116 n=338

Last 30

63.8%

803–455 n=1258

Prev 30

63.5%

106–61 n=167

Season

63.8%

909–516 n=1425

All time

63.8%

909–516 n=1425

By month

MonthRecordHit ratevs base

2026-07106–6163.5% n=167+2.9 pp base 61%

2026-08803–45563.8% n=1258+3.2 pp base 61%

Model versions

VersionActiveRecordHit ratevs base

MLB Batter Hits

batter-hit-v62026-08-21→2026-08-29288–15465.2% n=442+4.5 pp base 61%

4 earlier versions2026-07-05→2026-08-20621–36263.2% n=983+2.6 pp base 61%

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.