Modeling the Quality of Player Passing Decisions in Australian Rules Football Relative to Risk, Reward, and Commitment

Abstract

The value of player decisions has typically been measured by changes in possession expectations, rather than relative to the value of a player’s alternative options. This study presents a mathematical approach to the measurement of passing decisions of Australian Rules footballers that considers the risk and reward of passing options. A new method for quantifying a player’s spatial influence is demonstrated through a process called commitment modeling, in which the bounds and density of a player’s motion model are fit on empirical commitment to contests, producing a continuous representation of a team’s spatial ownership. This process involves combining the probability density functions of contests that a player committed to, and those they did not. Spatiotemporal player tracking data was collected for AFL matches played at a single stadium in the 2017 and 2018 seasons. It was discovered that the probability of a player committing to a contest decreases as a function of their velocity and of the ball’s time-to-point. Furthermore, the peak density of player commitment probabilities is at a greater distance in front of a player the faster they are moving, while their ability to participate in contests requiring re-orientation diminishes at higher velocities. Analysis of passing decisions revealed that, for passes resulting in a mark, opposition pressure is bimodal, with peaks at spatial dominance equivalent to no pressure and to a one-on-one contest. Density of passing distance peaks at 17.3 m, marginally longer than the minimum distance of a legal mark (15 m). Conversely, the model presented in this study identifies long-range options as have higher associated decision-making values, however a lack of passes in these ranges may be indicative of differing tactical behavior or a difficulty in identifying long-range options.

Team numerical advantage in Australian rules football: A missing piece of the scoring puzzle?

“…Previous investigations have assessed the validity and reliability of similar match event data and reported very high levels (ICC range = 0.947-1.000) of agreement [13]. Positional data were synchronised with match event data using the unix timestamps present in both datasets [14], which was used to infer ball position. Field position of the ball was separated into four zones (defensive 50; D50, defensive mid; DM, attacking mid; AM, forward 50; F50) by the two 50 m arcs and the centre of the ground (see Fig 1), which is conventional for AF research and statistical providers [12,15,16].…”

Behavioral Spatial Segmentation and Its Application to Sports Dynamics

“…This is evident, for example, in the Barça Sports Analitics Summit held in 2019. In it, several works were developed in which, mostly, mathematical models were proposed to measure and represent the behavior of the team and the players in different contexts such as high-risk passes where the momentum of the player's movement is important for spatial control and interception of the ball based on contextual information (Spencer et al., 2019); in different types of formation, important for the evaluation of the aggressiveness of the team, the focus of attacks and the playing style (Shaw & Glickman, 2019); in the identification and classification of off-ball possession runs (Gregory, 2019); and an interesting technique to analyze the orientation of the players (Arbués-Sangüesa et al., 2019).…”

Quantifying congestion with player tracking data in Australian football

“…Previous investigations have assessed the validity and reliability of similar match event data and reported very high levels (ICC range = 0.947–1.000) of agreement [ 9 ]. Movement data derived from tracking devices were also recorded to the nearest tenth of a second and were synchronised with match event data using the unix timestamps present in both datasets [ 10 ]. This combined dataset was used to infer the location of the ball, which was also specified to the nearest tenth of a second.…”