Skip to content
Browse › Tennis Showcase
Analytics module · as of

Tennis Showcase

tennis has a served live model but no ingame_grade_joined corpus locally -- this showcase surfaces the two REAL preregistered gate receipts that ARE present (pregame cross-corpus + ingame surface-context detail layer), not a recomputed i...
View full size ↗
confirmednull (a finding)not testabledescriptivepending
Tennis Showcase
Chart: Tennis Showcase -- tennis has a served live model but no ingame_grade_joined corpus locally -- this showcase surfaces the two REAL preregistered gate receipts that ARE present (pregame cross-corpus + ingame surface-context detail layer), not a recomputed i...
scripts/platformkit/analytics_showcase/out/tennis_showcase.json

What it means

The base (state, time) model, fit on one tour and tested leak-free on the other, is beaten by adding the prior in both directions, calibration only, no market claim. But making the hold prior surface-specific does not help: the pooled Brier change is only +0.000121 on ATP and +0.002492 on WTA, so the planted null dies.

Caveats & confounds

CALIBRATION only (held-out Brier / Diebold-Mariano), never a market edge or dollar claim. Tennis has a served live model but no in-game grade corpus locally, so this surfaces the two receipts that exist, not a recomputed in-game summary.

Ask Scout about this
Does a tennis prior trained on one tour transfer to the other?Did the surface-specific tennis prior beat the surface-blind one?Ask anything →