Brandin Podziemski

Golden State Warriors

SG 6-5 205 lb 2 yr exp Illinois
2.4 Predictability score 39 games started, 2025-26
Season 2025-26 season backtest

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.

StatAvgModel MAENaive MAESkill
Points 15.54 5.11 5.08 +7.7%
Rebounds 5.41 2.17 2.1 -2.9%
Assists 4.1 2.12 2.09 -0.5%
3PM 1.92 1.11 1.13 +3.3%

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

DateOpponent PointsReboundsAssists3PM
2026-04-12 @ Los Angeles Clippers 10 (15.9) 4 (4.6) 2 (3.4) 2 (2.3)
2026-04-10 @ Sacramento Kings 30 (16.1) 3 (4.6) 1 (3.9) 3 (2.1)
2026-04-09 vs Los Angeles Lakers 17 (16.1) 1 (4.7) 1 (3.9) 1 (2.3)
2026-04-07 vs Sacramento Kings 20 (17.0) 1 (5.7) 3 (4.6) 4 (2.2)
2026-04-05 vs Houston Rockets 18 (16.6) 2 (5.6) 3 (4.4) 2 (2.1)
2026-04-02 vs Cleveland Cavaliers 25 (16.7) 4 (5.9) 4 (4.7) 2 (2.2)
2026-04-01 vs San Antonio Spurs 14 (15.6) 6 (5.3) 5 (3.9) 2 (2.2)
2026-03-29 @ Denver Nuggets 23 (16.2) 5 (5.5) 2 (3.7) 5 (2.3)
2026-03-27 vs Washington Wizards 22 (15.9) 10 (5.7) 7 (4.3) 3 (2.1)
2026-03-25 vs Brooklyn Nets 22 (14.2) 6 (4.9) 5 (3.9) 2 (1.9)
2026-03-23 @ Dallas Mavericks 20 (15.3) 10 (5.0) 6 (4.1) 2 (2.1)
2026-03-21 @ Atlanta Hawks 5 (15.5) 0 (5.5) 1 (4.2) 0 (2.3)
2026-03-20 @ Detroit Pistons 15 (14.4) 6 (4.6) 3 (3.8) 2 (2.1)
2026-03-18 @ Boston Celtics 10 (13.9) 6 (5.3) 5 (4.0) 1 (2.1)
2026-03-16 @ Washington Wizards 10 (16.1) 4 (5.7) 3 (4.5) 1 (2.2)
2026-03-15 @ New York Knicks 25 (14.2) 5 (5.0) 6 (4.1) 2 (2.4)
2026-03-13 vs Minnesota Timberwolves 25 (15.4) 10 (5.1) 2 (4.0) 5 (2.2)
2026-03-10 vs Chicago Bulls 9 (15.6) 2 (5.9) 7 (4.3) 1 (2.2)
2026-03-09 @ Utah Jazz 14 (16.7) 8 (5.2) 4 (4.5) 4 (2.3)
2026-03-07 @ Oklahoma City Thunder 17 (14.8) 6 (6.1) 6 (3.6) 3 (2.0)
2026-03-05 @ Houston Rockets 26 (16.3) 9 (6.1) 1 (4.3) 4 (2.1)
2026-03-02 vs Los Angeles Clippers 22 (15.7) 7 (6.4) 3 (4.6) 3 (2.0)
2026-02-28 vs Los Angeles Lakers 9 (15.9) 7 (6.1) 6 (4.4) 0 (2.1)
2026-02-25 @ Memphis Grizzlies 19 (15.6) 8 (6.0) 6 (4.1) 3 (1.9)
2026-02-03 vs Philadelphia 76ers 8 (15.7) 2 (5.3) 2 (5.4) 2 (1.6)
2026-01-30 vs Detroit Pistons 11 (14.8) 8 (4.5) 8 (4.1) 1 (1.7)
2026-01-28 @ Utah Jazz 11 (16.3) 8 (4.8) 7 (4.3) 1 (1.9)
2026-01-26 @ Minnesota Timberwolves 12 (14.7) 7 (4.4) 4 (3.7) 0 (1.9)
2026-01-25 @ Minnesota Timberwolves 12 (15.4) 5 (4.6) 6 (3.6) 0 (2.1)
2026-01-22 @ Dallas Mavericks 9 (15.8) 4 (5.1) 10 (3.3) 0 (2.0)
2026-01-20 vs Toronto Raptors 11 (14.0) 3 (4.3) 2 (3.1) 1 (2.0)
2026-01-02 vs Oklahoma City Thunder 12 (12.9) 4 (4.0) 4 (3.3) 1 (2.2)
2025-12-04 @ Philadelphia 76ers 6 (14.2) 6 (4.2) 0 (3.5) 0 (2.0)
2025-12-02 vs Oklahoma City Thunder 17 (14.7) 4 (4.0) 4 (3.1) 3 (2.4)
2025-11-29 vs New Orleans Pelicans 15 (15.8) 5 (4.5) 6 (3.6) 3 (2.3)
2025-11-19 @ Miami Heat 20 (13.8) 8 (4.8) 2 (2.6) 2 (2.3)
2025-11-09 vs Indiana Pacers 14 (14.5) 6 (4.3) 1 (4.9) 1 (2.1)
2025-11-07 @ Denver Nuggets 7 (13.2) 2 (4.2) 3 (3.8) 1 (2.3)
2025-11-05 @ Sacramento Kings 14 (15.8) 9 (4.3) 9 (3.6) 2 (2.5)

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.