Ajay Mitchell
Oklahoma City Thunder
Projected vs actual profile
Season averages, axes scaled to an elite starter level.
Model vs naive baseline
The naive forecaster projects the average of season and last-5 games. We publish the comparison for every stat, whichever side wins.
| Stat | Avg | Model MAE | Naive MAE | Skill |
|---|---|---|---|---|
| Points | 15.96 | 4.67 | 4.98 | +5.9% |
| Rebounds | 3.65 | 1.15 | 1.34 | +12.2% |
| Assists | 4.04 | 1.69 | 1.84 | +5.4% |
| 3PM | 1.26 | 0.79 | 0.77 | +1.6% |
Skill = CRPS improvement of the full probability distribution over a Poisson naive, per game. Points and rebounds drive the headline score; assists and threes are shown for transparency.
Game by game: predicted vs actual
The shaded band is the model's 10th to 90th percentile before tip-off. Dots are what he actually did.
Every game he started
| Date | Opponent | Points | Rebounds | Assists | 3PM |
|---|---|---|---|---|---|
| 2026-05-22 | @ San Antonio Spurs | 2 (15.3) | 5 (3.8) | 1 (3.7) | 0 (1.3) |
| 2026-05-11 | @ Los Angeles Lakers | 28 (17.0) | 3 (3.4) | 4 (3.8) | 1 (1.7) |
| 2026-05-09 | @ Los Angeles Lakers | 24 (16.1) | 4 (3.4) | 10 (3.6) | 2 (1.6) |
| 2026-05-07 | vs Los Angeles Lakers | 20 (15.7) | 3 (3.5) | 6 (3.4) | 0 (1.7) |
| 2026-05-05 | vs Los Angeles Lakers | 18 (16.1) | 2 (3.8) | 4 (3.5) | 1 (1.6) |
| 2026-04-27 | @ Phoenix Suns | 22 (14.4) | 4 (4.4) | 6 (2.9) | 4 (1.4) |
| 2026-04-25 | @ Phoenix Suns | 15 (13.1) | 6 (4.2) | 2 (3.1) | 1 (1.3) |
| 2026-04-07 | @ Los Angeles Lakers | 9 (13.8) | 3 (3.4) | 3 (3.6) | 1 (1.5) |
| 2026-03-30 | vs Detroit Pistons | 14 (13.5) | 2 (3.3) | 3 (3.7) | 0 (1.2) |
| 2026-03-21 | @ Washington Wizards | 14 (15.9) | 1 (4.4) | 3 (3.8) | 2 (1.3) |
| 2026-03-18 | @ Brooklyn Nets | 10 (15.6) | 7 (4.0) | 2 (3.5) | 0 (1.3) |
| 2026-03-17 | @ Orlando Magic | 16 (15.9) | 2 (3.8) | 3 (3.7) | 1 (1.4) |
| 2026-03-15 | vs Minnesota Timberwolves | 11 (16.9) | 5 (3.8) | 3 (3.9) | 1 (1.4) |
| 2026-03-12 | vs Boston Celtics | 15 (16.8) | 4 (3.9) | 6 (3.3) | 1 (1.4) |
| 2026-01-21 | @ Milwaukee Bucks | 18 (14.6) | 3 (3.9) | 2 (3.5) | 2 (1.3) |
| 2026-01-09 | @ Memphis Grizzlies | 23 (14.6) | 3 (3.8) | 6 (3.8) | 2 (1.4) |
| 2025-12-07 | @ Utah Jazz | 7 (15.6) | 2 (3.2) | 4 (4.2) | 1 (1.5) |
| 2025-12-02 | @ Golden State Warriors | 10 (15.6) | 4 (3.7) | 3 (3.8) | 2 (1.4) |
| 2025-11-12 | vs Los Angeles Lakers | 14 (18.9) | 3 (4.0) | 3 (4.3) | 1 (1.5) |
| 2025-11-11 | vs Golden State Warriors | 17 (18.5) | 3 (4.3) | 2 (3.9) | 2 (1.5) |
| 2025-11-09 | @ Memphis Grizzlies | 21 (18.8) | 6 (4.1) | 4 (3.9) | 2 (1.6) |
| 2025-11-07 | @ Sacramento Kings | 18 (19.2) | 5 (3.9) | 10 (4.0) | 2 (2.0) |
| 2025-11-05 | @ Portland Trail Blazers | 21 (17.8) | 4 (4.1) | 3 (3.3) | 0 (1.8) |
Bold = actual, in brackets = model projection before the game. Only games he started are shown: our projections assume the starting five, so a scratch is not a model miss.
About this data
The 2025-26 season is a holdout backtest: the models were trained and validated only on seasons up to 2024-25, then predicted every 2025-26 game. The season is fully out-of-sample, with one caveat: historical features use realized lineups, while live production predicts from the expected starting five, so live accuracy can run marginally lower. Projections and full distributions for today's games are on the NBA player projections page, and the methodology behind every model is on the methodology page.