Model CLV: aggregate audit

Closing-line-value audit of the platform's picks: the ones we recommended, and every market we priced. CLV = closing price − the price we took, raw implied on both sides. The model is not in that formula, which is what makes it a test rather than a restatement of our own opinion. Positive mean CLV means our picks beat the close, the standard proxy for sharp skill.

+1.44pp
Beating the close. Above our target, on a sample too small to call that settled.
Mean closing-line value across 241 recommended picks with a closing line; the price moved our way on 51.9% of them. 95% range +0.6 to +2.3pp.

Both prices are the best on the board at their moment, when we posted and at the last capture before kickoff: this measures whether the market came toward us after we posted, not any one book's close.

Since 5 October 2026 our model starts from the market's price, so calls are rarer. Earlier calls stay in this record.

-0.62pp
Not beating the close.
Every market we priced, recommended or not: 10,030 markets; the price did not move our way on 61.2% of them. 95% range -0.7 to -0.5pp, 1.62pp short of our +1.00pp target.

This is the model's raw number, before the selection gate, and the one the plan below is about.

Bar for selling picks +0.00pp Target +1.00pp
Window (by game date):
30 days 90 days All time Since 12 Sep fix
View:
Per sport By sport + bet type
Methodology: The close is the last price captured before kickoff, and a row is recomputed whenever a fresher close is captured. Buckets with N<30 are hidden. The Since 12 Sep fix window starts at the closing-line capture fix of 12 September 2026, the cohort the selling test is judged on. CLV compares the best price available when we posted the pick with the best price available at the last capture before kickoff. Both ends are best-of-board, and the close is captured across at least as many books as the board we post from, Pinnacle where it is quoted, so the comparison does not tilt in our favour.

Every market we priced, by sport and market

Every market we priced, by sport and market: model CLV per bucket.
Sport Market N Mean CLV Median CLV % beating close
MLB Moneyline 2,102 -0.61pp -0.57pp 37.7%
MLB Spread 1,186 -0.60pp -0.62pp 38.4%
WTA Tennis Moneyline 1,116 -0.54pp -0.38pp 38.5%
ATP Tennis Moneyline 1,085 -0.72pp -0.52pp 40.3%
MLB Over/Under 699 +0.13pp +0.00pp 47.4%
UFC Moneyline 457 -1.20pp +0.00pp 47.3%
NCAAF Moneyline 418 -2.36pp -1.68pp 26.1%
NBA Moneyline 287 -0.61pp -0.15pp 44.6%
NHL Moneyline 270 -0.47pp -0.19pp 37.8%
NHL Spread 237 -0.23pp -0.43pp 38.0%
La Liga Moneyline 196 -2.10pp -2.09pp 31.1%
Serie A Moneyline 173 +0.17pp -1.48pp 34.1%
UFC Over/Under 157 -0.70pp -0.82pp 40.8%
EPL Moneyline 154 +0.46pp -1.16pp 42.2%
NHL Over/Under 144 +0.68pp +0.00pp 45.8%
Bundesliga Moneyline 128 +1.47pp -0.60pp 46.1%
NFL Moneyline 105 -3.11pp -2.16pp 40.0%
NCAAF Spread 88 -0.87pp -0.68pp 12.5%
Ligue 1 Moneyline 81 -1.52pp -1.85pp 40.7%
Serie A Over/Under 76 -1.88pp -2.27pp 34.2%
Champions League Moneyline 75 +2.21pp† -2.42pp 38.7%
NCAAB Moneyline 73 +1.30pp +0.63pp 58.9%
NCAAF Over/Under 73 -0.67pp -0.47pp 9.6%
La Liga Over/Under 71 -1.09pp -2.12pp 32.4%
EPL Over/Under 70 -1.48pp -2.07pp 34.3%
Ligue 1 Over/Under 54 -1.03pp +0.00pp 48.1%
Bundesliga Over/Under 48 +1.37pp +0.31pp 52.1%
EPL Spread 43 -0.85pp -0.99pp 30.2%
IPL Cricket Moneyline 41 -0.60pp +0.00pp 41.5%
La Liga Spread 41 -1.38pp -0.75pp 41.5%
Champions League Over/Under 34 +1.47pp +0.56pp 52.9%
Bundesliga Spread 33 +0.06pp +0.23pp 51.5%
Serie A Spread 33 -1.79pp -1.89pp 33.3%
NBA Spread 31 -0.55pp -0.24pp 22.6%

† mean and median differ by 3pp or more: a few large moves drive this cell.

Cumulative-mean CLV trajectory

Cumulative mean CLV, every market we priced · N=10,030 · 17 Mar 2026 to 29 Oct 2026 · ends at -0.62pp

What we are doing about it

A number like the one above is worth little without the response to it, so here is ours, and the figure that will show whether it worked.

  1. Narrow to where we are least behind. CLV is not evenly distributed. Today the largest sample is MLB, 3,987 markets at -0.48pp, and the widest gap is NFL, -2.74pp on 126. Coverage follows the evidence rather than the calendar.
  2. Pull the model toward the market where it disagrees most. In the band where our probability departs furthest from the closing price, the market has been the better estimator. That is a calibration problem with a known direction, not a mystery.
  3. Fix the instrument before trusting it. Some of what this page measured was measurement error, found and corrected in September 2026. Numbers here predate and postdate those fixes; the trajectory above, by game date, is the honest view.

The test: mean CLV on the picks we recommend, non-negative at 95% confidence. Today, on this window: +1.44pp, range +0.6 to +2.3pp, on 241 picks. Clears the bar. Declaring the record open is a decision we make in the open, with the reason stated here, not a switch this page flips.

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