Volume 18, Issue 2

Former NBA all-star forward Rasheed Wallace popularized the catchphrase “Ball Don’t Lie.” Rasheed would often shout this after an opponent missed a free throw. It was used by Rasheed to illustrate the mental impact on a free throw shooter from knowing the foul was questionable and its impact on likelihood of converting the ensuing free throw. The tendency to miss free throws associated with questionable foul calls—or the propensity for the ball to miss—would be followed by Rasheed’s “Ball Don’t Lie!” exclamation. This paper aims to test whether the ball was less likely to go through the hoop during free throws following questionable foul calls. We use a proxy to identify the questionableness of a foul call, one that Rasheed Wallace was very familiar with—whenever the original shooting foul was immediately followed by a technical foul. This proxy is meant to capture player and coach reactions to a shooting foul call. If the call was bad, or questionable, we expect more outrage from the team the foul was called on, which tends to draw technical fouls. Our findings do not support Rasheed’s prediction; the propensity to make a shooting foul free throw does not appear to change after a technical. In fact, using a subset of our data period under which the NBA changed technical foul rules to target complaining about foul calls, we find a small increase in free throw percentage after a technical foul call.

With the vast amount of data collected on football and the growth of computing power, many games involving decision choices can be optimized. The underlying rule is the maximization of an expected utility of outcomes and the law of large numbers. The data available allows one to compute with high accuracy the probabilities of outcomes of actions, and the well defined points system in the game allows for a specification of the terminal utilities. With some well established decision theory we can optimize choices for each single play level. A full exposition of the theory and analysis is presented in the paper.

In NCAA Division III Wrestling, the question arose how to assign schools to regions in a way that optimizes fairness for individual wrestlers aspiring to the national tournament. The problem fell within cluster analysis but no known clustering algorithms supported its complex and interrelated set of needs. We created several bespoke clustering algorithms based on various heuristics (balanced optimization, weighted spatial clustering, and weighted optimization rectangles) for finding an optimal assignment, and tested each against the generic technique of genetic algorithms. While each of our algorithms had different strengths, the genetic algorithm achieved the highest value on our objective function, including when comparing it to the region assignments that preceded our work. This paper therefore demonstrates a technique that can be used to solve a broad category of clustering problems that arise in athletics, particularly any sport in which athletes compete individually but are assigned to regions as a team.

Value functions are used in sports to determine the optimal action players should employ. However, most literature implicitly assumes that players can perform the prescribed action with known and fixed probability of success. The effect of varying this probability or, equivalently, “execution error” in implementing an action (e.g., hitting a tennis ball to a specific location on the court) on the design of optimal strategies, has received limited attention. In this paper, we develop a novel modeling framework based on Markov reward processes and Markov decision processes to investigate how execution error impacts a player’s value function and strategy in tennis. We power our models with hundreds of millions of simulated tennis shots with 3D ball and 2D player tracking data. We find that optimal shot selection strategies in tennis become more conservative as execution error grows, and that having perfect execution with the empirical shot selection strategy is roughly equivalent to choosing one or two optimal shots with average execution error. We find that execution error on backhand shots is more costly than on forehand shots, and that optimal shot selection on a serve return is more valuable than on any other shot, over all values of execution error.

Choosing the right defensive corner-strategy is a crucial task for each coach in professional football (soccer). Although corners are repeatable and static situations, due to their low conversion rates, several studies in literature failed to find useable insights about the efficiency of various corner strategies. Our work aims to fill this gap. We hand-label the role of each defensive player from 213 corners in 33 matches, where we then employ an augmentation strategy to increase the number of data points. By combining a convolutional neural network with a long short-term memory neural network, we are able to detect the defensive strategy of each player based on positional data. We identify which of seven well-established roles a defensive player conducted (player-marking, zonal-marking, placed for counterattack, back-space, short defender, near-post, and far-post). The model achieves an overall weighted accuracy of 89.3%, and in the case of player-marking, we are able to accurately detect which offensive player the defender is marking 80.8% of the time. The performance of the model is evaluated against a rule-based baseline model, as well as by an inter-labeller accuracy. We demonstrate that rules can also be used to support the labelling process and serve as a baseline for weak supervision approaches. We show three concrete use-cases on how this approach can support a more informed and fact-based decision making process.