AI Picks Track Record
Every AI pick is graded the moment its game goes final and written to an immutable ledger — the recommended side, the confidence, the odds it was made at, and the result. Nothing is edited after the fact. Every number below is computed live from that ledger, wins and losses alike.
Results assume a flat 1-unit stake on every “strong” or “lean” pick at the recommended side's money line. Picks the AI graded “no-pick” (no real edge) are never counted. For informational purposes only — not betting advice. 21+.
Closing Line Value (CLV)
CLV measures whether each pick beat the market's closing line — the price a game settles at right before kickoff. Consistently securing a better number than the close is the sharpest evidence of a genuine edge, and a far more stable signal than a short-run win rate.
Building — CLV appears once picks with a captured closing line settle. We snapshot each game's money line right up to kickoff, then compare it to the price the pick was made at.
3 picks with a captured closing line in flight — CLV posts as they settle.
Confidence calibration
Picks grouped by the confidence the AI assigned. A well-calibrated model's dots hug the dashed diagonal: picks it rates 70% should win about 70% of the time. Larger dots = more settled picks in that band.
Where the edge lives
The same immutable ledger, sliced different ways. A single ROI number hides as much as it reveals — this shows which kinds of picks actually carry the performance.
Does the AI win more when it commits harder? Strong picks should outperform leans.
| Segment | Record | Win% | Units | ROI | Avg CLV |
|---|---|---|---|---|---|
| Lean | 33-61-4 | 35% | -33.2 | -33.8% | — |
Record is W-L-P. ROI is net units over bets staked in that segment. Avg CLV is the mean implied-probability edge vs. the closing line (only picks with a captured close count). Small samples are noisy — weigh segments by their bet count.
By league
| League | Record | Win% | Units |
|---|---|---|---|
| MLB | 11-25-0 | 31% | -14.2 |
| ATP | 7-15-0 | 32% | -8.8 |
| WTA | 8-12-0 | 40% | -7.9 |
| UFC | 4-3-4 | 57% | +0.9 |
| WNBA | 3-4-0 | 43% | -1.2 |
| T20 | 0-2-0 | 0% | -2.0 |
Recent results
- Goncalo Da Rosa Castro (+1818)Kyrian Jacquet @ Goncalo Da Rosa Castro · ATP · 0-2-1.00u55% conf
- Niklas Waldner (+2099)Niklas Waldner @ Laslo Djere · ATP · 2-0-1.00u60% conf
- Juan Carlos Prado Angelo (+134)Taro Daniel @ Juan Carlos Prado Angelo · ATP · 0-2-1.00u55% conf
- Somerset County Cricket Club (-146)Somerset County Cricket Club @ Northamptonshire Steelbacks · T20 · 143-126-1.00u65% conf
- Mitch Ramirez (+300)Chase Hooper @ Mitch Ramirez · UFC · 0-0+0.00u75% conf
- Kamaru Usman Usman (+183)Dricus Du Plessis @ Kamaru Usman Usman · UFC · 137-148-1.00u65% conf
- Jared Cannonier Cannonier (+330)Jared Cannonier Cannonier @ Christian Duncan · UFC · 89-82-1.00u70% conf
- Adolfo Daniel Vallejo (+178)Adolfo Daniel Vallejo @ Valentin Vacherot · ATP · 0-2+1.78u62% conf
- Vicente Luque (-104)Vicente Luque @ Tresean Gore · UFC · 89-82-1.00u55% conf
- Neil Magny (+124)Neil Magny @ Ramiz Brahimaj · UFC · 0-0+0.00u55% conf
- Los Angeles Dodgers (+110)Milwaukee Brewers @ Los Angeles Dodgers · MLB · 1-4-1.00u55% conf
- Houston Astros (-120)Seattle Mariners @ Houston Astros · MLB · 5-10-1.00u58% conf
Methodology
- Each pick is snapshotted at the odds it was made at and graded against the final score. The row is append-only and never edited after settlement.
- Profit uses a flat 1-unit stake. A winning +150 pick returns +1.50u; a winning -200 pick returns +0.50u; a loss is -1u; a push is 0.
- Only disciplined bets count. Picks the model grades “no-pick” (no real edge vs. the market) are excluded entirely, so ROI reflects actionable picks only.
- Win rate excludes pushes. ROI is net units divided by the number of bets with money staked.
- Closing Line Value (CLV)compares each pick's price to the money line captured just before kickoff, in implied-probability points. Only picks with a captured closing line count toward the CLV sample — the raw ledger is never altered to compute it.