🏓
DeuceLab
Ratings & Predictions
Live

Track record

Every prediction we make is graded against the real result — walk-forward, using only what was known before the match. No hindsight, no cherry-picking, and no "value bet" claims. This is the whole record.

57.8%
Pick accuracy
0.237
Brier score
543.964
Graded predictions
’16
Tracking since 2016

592.457 matches · 9.729 players tracked across 9 leagues in 3 sports.

Track record over time
62 months · 543.964 graded · avg Brier 0.222

Monthly Brier from each match's pre-match prediction (walk-forward, no hindsight). A flat line below the 0.25 coin-flip mark means the model stays calibrated month after month — no drift.

Nov19coin-flip 0.25Aug26
Mar
0.238
58% · 29.792
Apr
0.239
58% · 29.378
May
0.237
58% · 31.044
Jun
0.236
59% · 29.932
Jul
0.235
59% · 30.006
Aug
0.235
59% · 8.661

Calibration

The real test of an honest probability: when we say 60%, does it happen about 60% of the time? Each dot is a band of predictions (543.964 graded); dot size = sample. On the dashed diagonal = perfectly calibrated — above it we were too cautious, below it too confident.

All sports

On the diagonal = honest. Above it = the model was too cautious, below = overconfident.

50%80%Predicted win %Actual win %
By sport
Table Tennis
50%80%Predicted win %Actual win %
Badminton
50%80%Predicted win %Actual win %
Padel
45%85%Predicted win %Actual win %

Our win probability vs the closing line

The hardest test isn't just against results — it's against the sharpest forecaster money can buy. For 21.098 matches we line up our stated win probability against the closing line — a top bookmaker's fair odds with the margin stripped out, the number the whole betting market converges to by tip-off. On average we sit -0.85 pp from it — no systematic over- or under-confidence — and 48.9% of our calls land within 5 pp of the closing line. We don't beat it — nobody reliably does — but this shows how close an honest model stays to the sharpest price. Source: Betradar closing line.

Ours vs closing line

On the diagonal = honest. Above it = the model was too cautious, below = overconfident.

50%95%Our win %Closing-line %
-0.85pp
Avg gap from the close
5.16pp
Typical (median) gap
48.9%
Within 5 pp of the close
But who was actually right?

Sitting close to the closing line proves nothing on its own — you can hug the market and still be wrong. So here is the harder question, on the 20.985 of those matches that have since finished: who called them better? The honest answer is not us.

Closing linemore accurate
60.4%
Winners called
0.234
Brier (lower = better)
DeuceLab model
57.7%
Winners called
0.237
Brier (lower = better)

Same matches, same moment, scored the same way. The market is a few points ahead of us — it aggregates money, injuries, insider knowledge and last-minute news that a rating model never sees. We publish the gap instead of hiding it, because a forecast you can't check is worth nothing.

Set model vs market

Our set-win model — the same engine behind correct-score and handicap predictions — put to an independent cross-check. For 8.008 matches we compare our implied per-set win probability against the market's (a bookmaker's per-set odds, margin removed). On average we sit -0.09 pp from the market (typical gap 3.2 pp) — a check that our set distribution is market-consistent, not just fit to past results. Early sample; grows over time.

Per-set: ours vs market

On the diagonal = honest. Above it = the model was too cautious, below = overconfident.

35%70%Our per-set win %Market per-set win %
Biggest gapsOursMarketΔ
Viktor Ziakun vs Serhii Miroshnychenko62%35%+26.59
Andrii Tkachenko vs Leos Havrda66%41%+24.65
Andrii Tkachenko vs Tomas Kucera62%39%+23.57
Andrii Fastov vs Serhii Miroshnychenko48%25%+22.72
Oleg Gavryshko vs Roman Cherevko59%37%+22.32
Oleksandr Dukhovenko vs Roman Cherevko55%34%+21.79

By sport & league

Table Tennis

Badminton

Padel

LeagueAccBrierGrade
🎾Padel70.4%0.186Good

Totals & handicaps

Beyond who wins: how the model's points-total (over/under), set-handicap and points-handicap calls hold up against the real pre-game lines — same walk-forward grading, across table tennis & badminton.

52.1%
Over/Under accuracy
57.9%
Set-cover accuracy
3944%
Fav cover: called → real
Are these calls calibrated?

Same honesty test for the handicap markets: our stated cover probability (favourite −1.5) vs how often it really covered. On the diagonal = honest.

Cover · fav −1.5
30%90%Predicted cover %Actual cover %
Points-cover
30%80%Predicted cover %Actual cover %

Cover c→r = how often we called the favourite to cover vs how often they really did. The model slightly under-rates favourites' dominance — they cover a touch more than predicted.

What these numbers mean. A Brier score measures how close our probabilities are to outcomes — 0.25 is a coin-flip, lower is better. Accuracy is how often the favourite we name wins. The calibration grade reflects whether a stated 60% really happens 60% of the time. We tested our model against the closing market and found no reliable edge — so we sell transparency, not tips. How to read these numbers →