Skip to content

NBA model accuracy

National Basketball Association · 2026-27 regular season

Every final NBA game, forecast with only what was known the day before and then scored. Lower Brier and log loss are better; a coin flip scores 0.250 Brier. All leagues

Scorecard

Accuracy of each model on final games
ModelGamesBrierLog lossAccuracySkillCalib. error
Game simulator (backtest)1260.2360.66464.3%+6.7%7.5%
Elo1380.2460.68857.3%+2.9%11.2%
Base rate1380.2530.70049.3%—3.6%
Published forecasts7small sample0.2210.63371.4%+13.2%18.6%

Calibration

When a model gives the home side a 60% chance, does it win about 60% of the time? Dots on the dashed line mean yes; whiskers show the 90% range the observed rate could land in by chance.

Brier score by month

Early-season forecasts lean on last season's regressed ratings, so expect them to improve as games accumulate.

Head to head

Game simulator (backtest) vs Elo

126 games both forecast

Brier
0.236 vs 0.238
Log loss
0.664 vs 0.670
Accuracy
64.3% vs 58.7%

Game simulator (backtest) has the lower Brier score here.

Published forecasts vs Game simulator (backtest)

7 games both forecast

Brier
0.221 vs 0.212
Log loss
0.633 vs 0.616
Accuracy
71.4% vs 85.7%

Game simulator (backtest) has the lower Brier score here, but on too few games to call.

Market consensus isn't connected: it needs a licensed odds source, which an admin can import. Until then the base rate and Elo are the benchmarks.

How this is measured

The backtest replays the game simulator for every final game from the efficiency ratings and Elo as they stood before that date, the league's scoring and home advantage so far, rest and travel, the venue and the game's weather. Injuries and lineups of past games aren't on record, so the replay is team level; the published forecasts, which include them, are scored separately as they accumulate.

Brier = ½ Σ (probability − outcome)² over home, away. Log loss = −ln(probability given to the result), with probabilities clipped at 0.5%. Tied finals are left out. Full details are in the model methodology document.

Pick record

Every forecast the site published before a game, scored once it finished. A pick is the likeliest outcome. A well-calibrated model's 70% picks come in about 70% of the time, so compare each row's hit rate with its confidence.

Record

5–2 71%

Average confidence 57%

Hit rate by confidence
Confidence PicksHit
Under 60%560%
60%–70%2100%
Latest picks
GamePickResult
Nov 6 BOS @ CHABOS 60%119–80
Nov 6 WAS @ ATLATL 58%132–139
Nov 6 PHI @ CLEPHI 55%95–119
Nov 6 OKC @ MEMMEM 58%128–97
Nov 6 TOR @ MILTOR 52%121–107
Nov 6 MIN @ NOPMIN 53%115–109
Nov 6 UTA @ DALDAL 65%100–112

Data as of Source: SportsAPI Pro

Cookies

Cookies keep you signed in. Optional ones remember your settings. No ads or tracking. Cookie policy