Zeus (American football)
Zeus is a computer program developed by End Game Technologies that models and predicts the outcomes of coaching decisions in American football games. The program is designed to produce statistical outputs showing the expected odds of winning given choices of potential play calls and roster choices. It is capable of simulating 1,000,000 games in a few seconds, and was developed using extensive research on historical data from National Football League games. It expresses its output in terms of Game Winning Chance, which is the probability that the specified team will win the current game. It also evaluates its output using a range of possible "worst case" scenarios to determine a Confidence Factor of 1 to 10 for its results.
Zeus is particularly geared toward evaluating situations where a coach has essentially two or three play decisions which the opposing team will recognize. An example would be if a team is on fourth down and short yardage, and needs to decide between trying to get first down, punting or kicking a field goal. In such a case, Zeus will output its analysis of the game winning chance if you punt versus if you try a short yardage play or kick the field goal. Another example would be, when your team is preparing to kick off, the chance of winning if you kick off normally versus attempting an onside kick.
An example of Zeus' output is its analysis of Super Bowl XL between the Pittsburgh Steelers and the Seattle Seahawks. Pittsburgh's play calling in "binary" situations exactly matched Zeus' evaluation of the optimal play choice. By contrast, Seattle's play calls differed in six instances, with a combined game winning probability difference of 8.40%, meaning that Zeus estimates that if Seattle had followed its play calls exactly then Seattle would have had an 8.4% better chance of winning the game.
Using Zeus' estimates of differences between its play calls and actual calls by coaches, the program's developers estimate that NFL teams lose on average roughly one game per season due to improper play choice in the binary situations described above.
One common example of where Zeus' recommendation differs with real life coaches is onside kicks. Coaches tend to avoid onside kicks as being too risky, but Zeus sometimes evaluates that the potential gain of a successful onside kick outweighs the risk of failing to recover the ball. Similarly, it tends to be more aggressive in trying for first down conversions, as the potential gain of a first down can outweigh the benefit of trying a safer play like a field goal. Overly emphasizing risk aversion and choosing the "safer" play is, according to Zeus, a shortcoming in human coaches.