Model CLV — Aggregate Audit

Per-sport closing-line-value audit on the platform's recommended picks. CLV = model implied prob − closing-market no-vig prob. Positive mean CLV means our picks consistently beat the close, the standard proxy for sharp skill.

Window:
30 days 90 days All time
View:
Per sport By sport + bet type
Methodology: CLV computed at game settlement against closing line (Pinnacle preferred, falls through to best-priced sharp book). Buckets with N<30 hidden until threshold met. Backfilled via OddsAPI historical-markets API; capture rate 84.3% (was 40.5% before 2026-05-10 fix).
Model CLV by sport and bet type.
Sport Bet type N Mean CLV Median CLV % beating close
CS2 (all) 30 -1.18pp +0.44pp 63.3%
EPL (all) 30 +1.51pp +1.98pp 60.0%
LALIGA (all) 38 -2.92pp -2.44pp 26.3%
MLB (all) 1,224 +3.49pp +2.50pp 65.2%
MMA_MIXED_MARTIAL_ARTS (all) 143 +2.16pp +0.60pp 59.4%
NBA (all) 36 +1.50pp +2.69pp 69.4%
NFL_PRESEASON (all) 97 +3.42pp +1.28pp 80.4%
TENNIS_ATP (all) 269 -1.55pp -1.41pp 37.9%
TENNIS_WTA (all) 256 +1.42pp +1.83pp 59.0%

Cumulative-mean CLV trajectory

cumulative mean CLV (pp) · N=2172+2.18pp

See /trust for live calibration buckets across sports and /methodology for the signal pipeline behind each pick.