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) 206 -2.60pp -1.70pp 40.3%
CRICKET_IPL (all) 85 -1.95pp -1.89pp 28.2%
CS2 (all) 43 -1.84pp +0.25pp 53.5%
EPL (all) 347 -1.24pp -0.70pp 46.7%
LALIGA (all) 306 -2.68pp -2.42pp 37.9%
LIGUE1 (all) 154 -3.98pp -2.95pp 40.9%
MLB (all) 6,909 +2.13pp +1.63pp 61.4%
MMA_MIXED_MARTIAL_ARTS (all) 836 -2.11pp -2.70pp 34.7%
NBA (all) 1,028 +1.86pp +1.17pp 61.7%
NCAAB (all) 297 +1.00pp +1.84pp 63.3%
NFL_PRESEASON (all) 101 +3.48pp +1.28pp 81.2%
NHL (all) 1,019 +0.65pp +0.22pp 51.7%
SERIEA (all) 319 -4.98pp -3.48pp 38.9%
TENNIS_ATP (all) 1,544 -4.18pp -3.58pp 26.8%
TENNIS_WTA (all) 1,517 -3.00pp -1.63pp 40.4%
UCL (all) 75 +2.96pp +4.07pp 66.7%

Cumulative-mean CLV trajectory

cumulative mean CLV (pp) · N=14786+0.08pp

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