Sports score is a method of scoring in team sport games. Typically, each competing team accumulates points by placing a ball or puck into their own basket or net within a game’s time limit. The team with the highest score is declared the winner. The most well-known basket/net sports are basketball and soccer, where players can win a point by putting the ball into their own team’s basketball hoop or kicking it into their own team’s soccer net. Racquet sports, such as tennis and badminton, may also use points-based scoring.

While there is growing interest in quantitative analysis and modeling of professional sports, relatively little is known about what patterns or principles cut across different sports. This article uses a novel, comprehensive data set of scoring events (timing and attribution) from a dozen seasons of college (CFB), NFL, NHL, and NBA games to identify several common patterns in both the tempo and balance of these events.

Specifically, we find that the timing of scoring events – how often an event occurs within a given period of gameplay – closely approximates a Poisson process, with a sport-specific rate. Similarly, the balance of scoring events – how often one team wins an event – is close to a Bernoulli model with a parameter that varies with the size of a team’s lead.

Moreover, the inter-arrival time distributions for these events exhibit a three-phase pattern: a relatively constant rate is depressed at the beginning of each scoring period, increases dramatically in the middle of the period, and then drops off again in the final seconds of the period. These patterns are all consistent with a first-order Markov model.