Advancing NHL Analytics through Explainable AI
Proceedings of the Canadian Conference on Artificial Intelligence · 27.05.2024
DOI: 10.21428/594757db.ec493180 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Canadian Conference on Artificial Intelligence, online erschienen am 27.05.2024. Verfasst von Miles Pitassi und 1 weiteren Autor:innen.
Abstract (Originalsprache)
This paper introduces a novel three-phase framework designed to enhance trust and explainability in the integration of artificial intelligence (AI) models within the National Hockey League (NHL). The proposed framework addresses key barriers to the wide-spread adoption of these models, namely: the need for explanations that cater to various stakeholders, the requirement for explanations to be tailored to specific machine learning models, and the challenge of ensuring model reliability and purpose. A case study demonstrates the framework’s effectiveness, using an AI model to predict power play performance based on player attributes. This research aims to bridge the gap between AI’s theoretical potential and its practical application in NHL sports analytics, positioning the framework as a key tool to enhance understanding and acceptance of these technologies.
Zitieren
APA
Pitassi, M., & Cohen, R. (2024). Advancing NHL Analytics through Explainable AI. Proceedings of the Canadian Conference on Artificial Intelligence. https://doi.org/10.21428/594757db.ec493180
Vancouver
Pitassi M, Cohen R. Advancing NHL Analytics through Explainable AI. Proceedings of the Canadian Conference on Artificial Intelligence. 2024. doi:10.21428/594757db.ec493180
BibTeX
@article{Pitassi2024,
author = {Pitassi, Miles and Cohen, Robin},
title = {Advancing NHL Analytics through Explainable AI},
journal = {Proceedings of the Canadian Conference on Artificial Intelligence},
year = {2024},
doi = {10.21428/594757db.ec493180}
}
EUVIMED