How NBA Totals Are Projected: Pace First, Then Efficiency

Every NBA total can be written as possessions multiplied by points per possession, for both teams. That identity is the backbone of our projected totals.

Possessions (pace)

We estimate possessions from the box score (field-goal attempts, minus offensive rebounds, plus turnovers, plus 0.44 of free-throw attempts, averaged over both teams) and express them per 48 minutes. Each team's pace is time-weighted so recent games count more; the matchup's pace combines both teams relative to the league average.

Efficiency, adjusted for opponents

Points per 100 possessions are adjusted for the quality of the defences a team has faced, and vice versa. A team that scored 118 against three top defences is better than one that scored 118 against three bad ones.

The scoring environment moves

League scoring rose sharply over the last decade. Our totals are anchored to the current league scoring environment (a rolling league average of efficiency and pace), and the model explains deviations from it. Without that anchor, a model trained on older seasons would under-project modern games.

Players and shot profile

The projected rotation's shooting volume, free-throw rate, three-point rate, turnovers, offensive rebounds and fouls all enter the total, so a team missing its high-volume scorer projects lower even before its team numbers catch up.

How accurate is it?

Totals are harder than margins: in the backtest the projected total missed by a little under 15 points on average. The 80% range shown on each game page reflects that honestly. See the projected totals.

📚 More Articles

How We Backtest an NBA Model Without Fooling Ourselves

Walk-forward testing, frozen settings and four untouched seasons: the rules that keep an NBA projection model honest.

What a 70% Win Probability Really Means

A 70% favourite loses three games in ten. Calibration, not bold calls, is what makes a probability useful.

Offensive, Defensive and Net Rating, Explained

Why points per 100 possessions beat points per game, and how opponent adjustment turns raw ratings into team strength.

The Four Factors: Shooting, Turnovers, Rebounding, Free Throws

Dean Oliver's four factors explain most of the gap between good and bad NBA teams. Here is how to read them.

Projections are statistical estimates for entertainment and analysis only. Nothing here guarantees any result.