Utilizing Tracking Data to Create Defensive Performance Indicators for Football Players

Suggested by: Philip Schnittkamp, https://www.plaier.com/

Supervisor: Christian Neuwirth 

Short description: Football (or otherwise known as soccer) is one of the most complex sports to analyze with data. The low-scoring nature of the sport, as well as the fact that 22 players are active on a huge pitch at the same time, are just some of the reasons for the huge complexity of modeling team and player strengths. While the analysis of so-called event data has taken huge strides over the last years and is arguably especially helpful when analyzing the individual performance of attacking players, the rise of tracking data allows for much more complex spatio-temporal analysis on both the collective (team) and individual (player) level. Since then, public research has often concentrated on analyzing offensive patterns such as attacking pitch control, passing decision optimization, or off-ball runs to create space. Although there have also been major advances in analyzing defensive patterns like pressing efficacy or defensive compactness, there are still enough areas on the defensive side that remain un- or at least underexplored, especially on the individual player level.

The main idea of this master thesis is to further develop upon existing ideas and models to measure defensive player performance based on tracking data, specifically in terms of optimal defensive positioning to suppress the opposition’s threat. The utilization of several different statistical methods is conceivable to achieve this goal: already existing pitch control frameworks, neural nets, agent-based modelling approaches, etc. While the ultimate goal is to create a defensive performance measure on the individual player level, this is inevitably connected to the team level: Any good individual performance measure should, in the best case, lead to team success in the end to demonstrate its validity.

The following research questions should guide the analysis:

• Which players (and teams) are effective in hindering their opponents from spatio-temporally controlling the most dangerous areas of the pitch?
• What are the optimal defensive positions each player can take on to suppress the opposition’s threat based on their teammates’ and opponents’ positioning at any given time?
• Which players (and teams) are effective in taking on (close to) optimal positions on the defensive side? Which players (and teams) are effective in lowering opponent threat in comparison to expectation based on the opponent’s usual performances?
• Can a team’s defending style influence these results? And does it make sense to quantify this based on different areas of the pitch and/or different phases of defending?
• Are some players better at positioning themselves optimally in different areas of the pitch and/or different phases of defending?
• Are teams that are more effective in terms of defensive positioning better at hindering opponents from scoring goals? Are they more successful overall?

Start/finish: Anytime.

Prerequisites/qualifications: Experience with coding in Python (preferrable) or R is required. Personal interest and at least basic knowledge in football would be highly beneficial.

Suggested reading:

• Spearman, W. (2016, February). Quantifying pitch control. In OptaPro Analytics Forum [Internet]. https://doi.org/10.13140/RG.2.2.22551.93603.
• Fernández, Javier & Bornn, Luke. (2018). Wide Open Spaces: A statistical technique for measuring space creation in professional soccer.
• Higgins, Lewis & Galla, Tobias & Prestidge, Brian & Wyatt, Terry. (2023). Measuring the pitch control of professional football players using spatiotemporal tracking data. Journal of Physics: Complexity. 4. https://doi.org/10.1088/2632-072X/acb67d.
• Spearman, W. (2018, February). Beyond expected goals. In Proceedings of the 12th MIT sloan sports analytics conference (pp. 1-17).
• Peters, Andrew & Parmar, Nimai & Davies, Michael & James, Nic. (2026). Applying an Expected Pass Turnovers model to inform pressing strategies in professional football. International Journal of Performance Analysis in Sport. 1-16. https://doi.org/10.1080/24748668.2026.2671547.
• Forcher, L., Beckmann, T., Wohak, O., Romeike, C., Graf, F., & Altmann, S. (2024). Prediction of defensive success in elite soccer using machine learning - Tactical analysis of defensive play using tracking data and explainable AI. Science and Medicine in Football, 8(4), 317–332. https://doi.org/10.1080/24733938.2023.2239766
• Forcher, L., Forcher, L., Altmann, S., Jekauc, D., & Kempe, M. (2024). Is a compact organization important for defensive success in elite soccer? – Analysis based on player tracking data. International Journal of Sports Science & Coaching, 19(2), 757-768.
• Forcher, L., Altmann, S., Forcher, L., Jekauc, D., & Kempe, M. (2022). The use of player tracking data to analyze defensive play in professional soccer - A scoping review. International Journal of Sports Science & Coaching, 17(6), 1567-1592.

 

Modeling Place Vulnerability to Explosive Disease Outbreaks

Suggested by: Christian Neuwirth (Z_GIS – Spatial Simulation)
 
Short description:

In addition to the basic reproduction number, R0, the overdispersion parameter, k, plays a crucial role in characterizing the spread of infectious diseases. Estimates for COVID-19 indicate that the dispersion parameter k is approximately 0.1, suggesting that 80% of transmissions have been caused by only 10% of infectious individuals [1]. 

Observed overdispersion can arise from various factors. For instance, the same pathogen may exhibit different behaviors across individuals, e.g. the infectious period is better represented as a distribution rather than a fixed constant [2]. 

Additionally, observed overdispersion in disease transmission may stem from overdispersion in social contact networks. For example, a French social contact survey caried out by [3] demonstrated that a small number of individuals account for a disproportionately large share of overall social contacts, while many individuals have few or no social interactions.
Modeling experiments indicate that outbreaks within such social networks tend to be particularly explosive (Fig. 1).

 
Figure 1. The blue curves represent simulated outbreaks in empirical social networks exhibiting overdispersion, while the red curves depict outbreaks in networks where every individual has an equal number of social contacts. The basic reproduction numbers are as follows: R0=1.8 (A), R0=2.5 (B), R0=3.1 (C), and R0=3.7 (D).
 

Hypothesis: It is hypothesized that overdispersion in social contact networks is influenced by the physical structures of space, such as transportation infrastructure and other elements of the built environment. For instance, recent investigations showed that hierarchical cities are more vulnerable to the rapid spread of infectious diseases than decentralized cities [4]. In other words, overdispersion in physical structures translates into overdispersion in social contact networks, which in turn leads to overdispersion in disease transmission and explosive outbreaks.

The aim of this thesis is to quantify the vulnerability of locations to epidemic outbreaks by analyzing their structural properties.

Method: (1) Quantify the overdispersion parameter k in physical infrastructures using data from OpenStreetMap, MobilityDatabase GTFS Feeds or open air travel network data (with the appropriate scale to be determined), (2) Run network simulations in a SIR-model (model is available) using the empirical parameter k as an input, (3) Compare epidemic doubling time in the simulation with empirical COVID-19 excess mortality doubling time at selected sites using a ranking scale approach.

Start: ASAP

Prerequisites/qualifications: 
Interest in spatial simulation and scripting (NetLogo, Python, R or GAMA)

Please contact Christian Neuwirth in case of interest: christian.neuwirth@plus.ac.at

References:

1. K. Sneppen, B. F. Nielsen, R. J. Taylor, and L. Simonsen, “Overdispersion in COVID-19 increases the effectiveness of limiting nonrepetitive contacts for transmission control,” Proceedings of the National Academy of Sciences, vol. 118, no. 14, p. e2016623118, 2021.
2. A. L. Lloyd, “Destabilization of epidemic models with the inclusion of realistic distributions of infectious periods,” Proceedings of the Royal Society of London. Series B: Biological Sciences, vol. 268, no. 1470, pp. 985–993, 2001.
3. G. Béraud et al., “The French connection: the first large population-based contact survey in France relevant for the spread of infectious diseases,” PloS one, vol. 10, no. 7, p. e0133203, 2015.
4. J. Aguilar et al., “Impact of urban structure on infectious disease spreading,” Scientific reports, vol. 12, no. 1, p. 3816, 2022.
5. O. Wegehaupt, A. Endo, and A. Vassall, “Superspreading, overdispersion and their implications in the SARS-CoV-2 (COVID-19) pandemic: a systematic review and meta-analysis of the literature,” BMC Public Health, vol. 23, no. 1, p. 1003, 2023.

Simulation of household delivery

Suggested by: Harald Busta (Feibra GmbH) and Christian Neuwirth (Z_GIS – Spatial Simulation)

Short description: 

The household delivery of advertising leaflets is indispensable for Austian retailers. Millions of flyers are delivered to Austrian households every day. Delivery staff is in charge of delivering advertising materials within precisely defined areas. Up to now, the evaluation of delivery efforts relies on empirical estimates and data on address density and other regional characteristics. In order to enable a more accurate allocation of resources, a continuous improvement of estimates by methods of network analysis and geospatial simulation is crucial. 

The aim of this work is to fine-tune existing estimates by agent based network simulations for respective delivery areas. The necessary basic data such as digital territory structures, precisely located delivery addresses (all postal address codes) and all effort specifications such as the number of delivery points and necessary depot locations are available and can be used in this master-thesis without restrictions.

 

Start: ASAP

 

Prerequisites/qualifications: Introductory course in Spatial Simulation, Modelling or similar

 

Please contact Christian Neuwirth in case of interest: christian.neuwirth@plus.ac.at