我要吃瓜

Citation

Uribe A, Sanders S, Ehrlich J, Reade JJ & Singleton C (2025) Do Behavioral Considerations Cloud Penalty-Kick Location Optimization in Professional Soccer?. In: MIT Sloan Sports Analytics Conference, Sloan School of Management at Massachusetts Institute of Technology, Cambridge, Massachusetts, United States, 07.03.2025-08.03.2025. Cambridge, Massachusetts. https://www.sloansportsconference.com/research-papers/do-behavioral-considerations-cloud-penalty-kick-location-optimization-in-professional-soccer-game-theory-empirical-testing-using-polynomial-regression-and-ml-gradient-boosting

Abstract
In soccer, penalty kicks (PKs) are taken with fair regularity (~ once in four matches) and often constitute high-leverage, or game-pivotal, events given the sport’s low-scoring nature. In a tabulation of 294,970 international, professional league, and professional cup match results recorded on footystats.org, we find that 1-0 and 1-1 are the most common professional full-time match scorelines, occurring 17.9 and 11 percent of the time, respectively. These outcomes are followed by 2-1 (8.5%) and 0-0 (7.7%). Across all recorded match outcomes, average full-time goals per professional match are 2.85. In the 2022-23 EPL, matches averaged 0.26 PKs and 0.194 PK conversions, equivalent to about 6.8% of goals scored according to tabulations of data from transfermarket.com. In 2023-24, this percentage rose to 7.6%. Herein, we examine whether professional penalty-takers strictly optimize on expected conversion-rate when choosing shot location, or whether behavioral considerations, such as “looking credible” by not missing the goal space entirely, are also at play.

Notes
1 Classical/Statistical Game Theory & Empirical Testing using Polynomial and ML Regularized Lasso Regression Paper Track: Soccer Paper ID: 20251395 github.com/sdsander-syr/soccer_pk_shot_location