Research Papers

Amod Sahasrabudhe, Joris Bekkers

‍

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 uncover what factors make them successful in both men's and women's professional soccer. We demonstrate that gender-specific Graph Neural Networks outperform architecturally identical gender-ambiguous models in predicting the successful outcome of counterattacks using smaller sample sizes. And we show, using Permutation Feature Importance, which features have the highest impact on model performance.