Jayson Tatum
Boston Celtics
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 | 22.18 | 3.63 | 4.22 | +10.6% |
| Rebounds | 10.18 | 3.91 | 3.97 | +7.3% |
| Assists | 5.73 | 2.87 | 2.96 | +8.7% |
| 3PM | 3.0 | 1.24 | 1.31 | +8.7% |
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 |
|---|---|---|---|---|---|
| 2026-04-30 | @ Philadelphia 76ers | 17 (23.1) | 11 (9.3) | 3 (6.1) | 2 (2.8) |
| 2026-04-28 | vs Philadelphia 76ers | 24 (23.0) | 16 (9.0) | 4 (6.4) | 4 (2.9) |
| 2026-04-26 | @ Philadelphia 76ers | 30 (22.2) | 7 (9.2) | 11 (5.5) | 5 (2.8) |
| 2026-04-24 | @ Philadelphia 76ers | 25 (23.6) | 5 (10.3) | 7 (6.0) | 5 (2.5) |
| 2026-04-21 | vs Philadelphia 76ers | 19 (24.2) | 14 (9.3) | 9 (5.5) | 2 (2.8) |
| 2026-04-19 | vs Philadelphia 76ers | 25 (23.9) | 11 (9.9) | 7 (5.6) | 1 (2.7) |
| 2026-04-09 | @ New York Knicks | 24 (22.6) | 13 (8.7) | 8 (5.3) | 2 (3.1) |
| 2026-04-07 | vs Charlotte Hornets | 23 (23.7) | 5 (9.4) | 4 (5.8) | 3 (3.1) |
| 2026-04-05 | vs Toronto Raptors | 23 (24.8) | 13 (8.9) | 7 (5.5) | 2 (3.1) |
| 2026-04-03 | @ Milwaukee Bucks | 23 (23.8) | 11 (9.6) | 9 (5.6) | 4 (3.1) |
| 2026-04-01 | @ Miami Heat | 25 (22.8) | 18 (8.6) | 11 (5.0) | 4 (2.9) |
| 2026-03-29 | @ Charlotte Hornets | 32 (21.1) | 5 (7.8) | 8 (4.2) | 5 (2.8) |
| 2026-03-27 | vs Atlanta Hawks | 26 (20.8) | 12 (8.9) | 5 (4.5) | 2 (2.8) |
| 2026-03-25 | vs Oklahoma City Thunder | 19 (20.1) | 12 (8.3) | 7 (3.7) | 3 (2.9) |
| 2026-03-22 | vs Minnesota Timberwolves | 16 (22.1) | 11 (7.5) | 2 (3.9) | 2 (3.0) |
| 2026-03-20 | @ Memphis Grizzlies | 13 (22.9) | 9 (8.0) | 0 (4.5) | 2 (3.3) |
| 2026-03-18 | vs Golden State Warriors | 24 (22.1) | 10 (7.6) | 2 (4.5) | 5 (3.0) |
| 2026-03-16 | vs Phoenix Suns | 21 (22.3) | 7 (7.7) | 4 (4.9) | 2 (3.2) |
| 2026-03-14 | vs Washington Wizards | 20 (22.6) | 14 (6.6) | 7 (4.3) | 2 (3.2) |
| 2026-03-10 | @ San Antonio Spurs | 24 (18.8) | 5 (6.6) | 2 (4.2) | 4 (2.6) |
| 2026-03-08 | @ Cleveland Cavaliers | 20 (17.0) | 3 (10.2) | 2 (6.3) | 2 (2.5) |
| 2026-03-06 | vs Dallas Mavericks | 15 (11.9) | 12 (5.0) | 7 (2.7) | 3 (0.8) |
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.