🔬 MIT Sloan Sports Analytics Conference Research Paper Competition 2023
On March 2nd 2023 Amod Sahasrabudhe and myself had the opportunity to present our research paper titled “A Graph Neural Network deep-dive into successful counterattacks”[pdf] as one of the finalists of the 2023 MIT Sloan Sports Analytics Conference Research Paper Competition.
The purpose of this research is to build gender-specific, first-of-their-kind Graph Neural Networks to model the likelihood of a counterattack being successful and to uncover what factors make them successful in both men’s and women’s professional soccer. These models are trained on a total of 20,863 frames of algorithmically identified counterattacking sequences from synchronized StatsPerform on-ball event and SkillCorner spatiotemporal (broadcast) tracking data. The data - easily accessible within the Counterattack Jupyter Notebook - is derived from 632 games of MLS (2022), NWSL (2022) and international women’s soccer (2020-2022).
More information on this research project can be found in the GitHub repository linked below.
Watch the presentation on YouTube below.
