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
BUNDESLIGA (all) 58 +2.45pp +4.39pp 65.5%
CS2 (all) 43 -1.84pp +0.25pp 53.5%
EPL (all) 101 -1.08pp -0.10pp 48.5%
LALIGA (all) 132 -2.70pp -1.90pp 43.2%
LIGUE1 (all) 70 -1.66pp -0.73pp 47.1%
MLB (all) 4,097 +3.01pp +1.93pp 63.6%
MMA_MIXED_MARTIAL_ARTS (all) 629 -0.33pp -1.45pp 40.2%
NBA (all) 120 +2.38pp +0.45pp 51.7%
NCAAB (all) 54 +3.19pp +3.48pp 79.6%
NFL_PRESEASON (all) 101 +3.48pp +1.28pp 81.2%
NHL (all) 119 +2.40pp +0.74pp 56.3%
SERIEA (all) 108 -6.76pp -4.45pp 38.9%
TENNIS_ATP (all) 1,058 -2.99pp -2.57pp 30.7%
TENNIS_WTA (all) 1,050 -1.12pp -0.21pp 48.5%
UCL (all) 39 +6.58pp +7.36pp 79.5%

Cumulative-mean CLV trajectory

cumulative mean CLV (pp) · N=7807+1.01pp

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